| 18.02 |
Google Brain |
USENIX Security 2021 |
The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks |
Memorization&LSTM |
| 19.12 |
Microsoft |
CCS2020 |
Analyzing Information Leakage of Updates to Natural Language Models |
Privacy Leakage&Model Update&Duplicated |
| 21.07 |
Google Research |
ACL2022 |
Deduplicating Training Data Makes Language Models Better |
Privacy Protected&Deduplication&Memorization |
| 21.10 |
Stanford |
ICLR2022 |
Large language models can be strong differentially private learners |
Differential Privacy&Gradient Clipping |
| 22.02 |
Google Research |
ICLR2023 |
Quantifying Memorization Across Neural Language Models |
Memorization&Verbatim Sequence |
| 22.02 |
UNC Chapel Hill |
ICML2022 |
Deduplicating Training Data Mitigates Privacy Risks in Language Models |
Memorization&Deduplicate Training Data |
| 22.05 |
UCSD |
EMNLP2022 |
An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models |
Privacy Risks&Memorization |
| 22.05 |
Princeton |
NIPS2022 |
Recovering Private Text in Federated Learning of Language Models |
Federated Learning&Gradient Based |
| 22.05 |
University of Illinois at Urbana-Champaign |
EMNLP2022(findings) |
Are Large Pre-Trained Language Models Leaking Your Personal Information? |
Personal Information&Memorization&Privacy Risk |
| 22.10 |
Google Research |
INLG2023 |
Preventing Generation of Verbatim Memorization in Language Models Gives a False Sense of Privacy |
Verbatim Memorization&Filter&Style Transfer Prompts |
| 23.02 |
University of Waterloo |
Security and Privacy2023 |
Analyzing Leakage of Personally Identifiable Information in Language Models |
PII Leakage&PII Reconstruction&Differential Privacy |
| 23.04 |
Hong Kong University of Science and Technology |
EMNLP2023(findings) |
Multi-step Jailbreaking Privacy Attacks on ChatGPT |
Privacy&Jailbreaks |
| 23.05 |
University of Illinois at Urbana-Champaign |
arxiv |
Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage |
Co-occurrence&PII |
| 23.05 |
The University of Texas at Dallas |
ACL2023 |
Controlling the Extraction of Memorized Datafrom Large Language Models via Prompt-Tuning |
Prompt-Tuning&Memorization |
| 23.05 |
Google Research |
NAACL2024(findings) |
Can Public Large Language Models Help Private Cross-device Federated Learning? |
Federated Learning&Large Language Models&Differential Privacy |
| 23.06 |
University of Illinois at Urbana-Champaign |
arxiv |
DECODINGTRUST: A Comprehensive Assessment of Trustworthiness in GPT Models |
Robustness&Ethics&Privacy&Toxicity |
| 23.08 |
Bern University of Applied Sciences |
NAACL2024(findings) |
Anonymity at Risk? Assessing Re-Identification Capabilities of Large Language Models in Court Decisions |
Anonymization&Re-Identification&Large Language Models |
| 23.09 |
UNC Chapel Hill |
arxiv |
Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks |
Hidden States Attack&Hidden States Defense&Deleting Sensitive Information |
| 23.09 |
Princeton University&Microsoft |
arxiv |
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation |
In-Context Learning&Differential Privacy |
| 23.10 |
ETH |
arxiv |
Beyond Memorization: Violating Privacy Via Inference with Large Language Models |
Context Inference&Privacy-Invasive&Extract PII |
| 23.10 |
Indiana University Bloomington |
CCS 2024 |
The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks |
Privacy risks&PII Recovery |
| 23.10 |
University of Washington & Allen Institute for Artificial Intelligence |
arxiv |
Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory |
Benchmark&Contextual Privacy&Chain-of-thought |
| 23.10 |
Georgia Institute of Technology |
arxiv |
Unlearn What You Want to Forget: Efficient Unlearning for LLMs |
Unlearning&Teacher-student Framework&Data Protection |
| 23.10 |
Tianjin University |
EMNLP2023 |
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models |
Privacy Neuron Detection&Model Editing&Data Memorization |
| 23.11 |
Zhejiang University |
arxiv |
Input Reconstruction Attack against Vertical Federated Large Language Models |
Vertical Federated Learning&Input Reconstruction&Privacy Concerns |
| 23.11 |
Georgia Institute of Technology, Carnegie Mellon University |
arxiv |
Reducing Privacy Risks in Online Self-Disclosures with Language Models |
Online Self-Disclosure&Privacy Risks&Self-Disclosure Abstraction |
| 23.11 |
Cornell University |
arxiv |
Language Model Inversion |
Model Inversion&Prompt Reconstruction&Privacy |
| 23.11 |
Ant Group |
arxiv |
PrivateLoRA for Efficient Privacy Preserving LLM |
Privacy Preserving&LoRA |
| 23.12 |
Drexel University |
arXiv |
A Survey on Large Language Model (LLM) Security and Privacy: The Good the Bad and the Ugly |
Security&Privacy&Attacks |
| 23.12 |
University of Texas at Austin, Princeton University, MIT, University of Chicago |
arxiv |
DP-OPT: MAKE LARGE LANGUAGE MODEL YOUR PRIVACY-PRESERVING PROMPT ENGINEER |
Prompt Tuning&Differential Privacy |
| 23.12 |
Delft University of Technology |
ICSE 2024 |
Traces of Memorisation in Large Language Models for Code |
Code Memorisation&Data Extraction Attacks |
| 23.12 |
University of Texas at Austin |
arXiv |
SentinelLMs: Encrypted Input Adaptation and Fine-tuning of Language Models for Private and Secure Inference |
Privacy&Security&Encrypted Input Adaptation |
| 23.12 |
Rensselaer Polytechnic Institute, Columbia University |
arXiv |
Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning |
Federated Learning&Differential Privacy&Efficient Fine-Tuning |
| 24.01 |
Harbin Institute of Technology Shenzhen&Peng Cheng Laboratory Shenzhen |
arxiv |
SecFormer: Towards Fast and Accurate Privacy-Preserving Inference for Large Language Models |
Privacy-Preserving Inference (PPI)&Secure Multi-Party Computing (SMPC)&Transformer Models |
| 24.01 |
NUS (Chongqing) Research Institute, Huawei Noah’s Ark Lab, National University of Singapore |
arxiv |
Teach Large Language Models to Forget Privacy |
Data Privacy&Prompt Learning&Problem Decomposition |
| 24.01 |
Princeton University, Google DeepMind, Meta AI |
arxiv |
Private Fine-tuning of Large Language Models with Zeroth-order Optimization |
Differential Privacy&Zeroth-order Optimization |
| 24.01 |
Harvard&USC&UCLA&UW Seattle&UW-Madison&UC Davis |
NAACL2024 |
Instructional Fingerprinting of Large Language Models |
Model Fingerprinting&Instructional Backdoor&Model Ownership |
| 24.02 |
Florida International University |
arxiv |
Security and Privacy Challenges of Large Language Models: A Survey |
Security&Privacy Challenges&Suevey |
| 24.02 |
Northeastern University, Carnegie Mellon University, Rensselaer Polytechnic Institute |
arxiv |
Human-Centered Privacy Research in the Age of Large Language Models |
Generative AI&Privacy&Human-Computer Interaction |
| 24.02 |
CISPA Helmholtz Center for Information Security |
arxiv |
Conversation Reconstruction Attack Against GPT Models |
Conversation Reconstruction Attack&Privacy risks&Security |
| 24.02 |
Columbia University, M365 Research, Microsoft Research |
arxiv |
Differentially Private Training of Mixture of Experts Models |
Differential Privacy&Mixture of Experts |
| 24.02 |
Stanford University, Truera ,Princeton University |
arxiv |
De-amplifying Bias from Differential Privacy in Language Model Fine-tuning |
Fairness&Differential Privacy&Data Augmentation |
| 24.02 |
Sun Yat-sen University, Google Research |
arxiv |
Privacy-Preserving Instructions for Aligning Large Language Models |
Privacy Risks&Synthetic Instructions |
| 24.02 |
National University of Defense Technology |
arxiv |
LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification |
Privacy Data Augmentation&Knowledge Distillation&Medical Text Classification |
| 24.02 |
Michigan State University, Baidu Inc. |
arxiv |
The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG) |
Privacy&Retrieval-Augmented Generation (RAG) |
| 24.02 |
University of Washington&Allen Institute for Artificial Intelligence |
NAACL2024 |
JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models |
Authorship Obfuscation&Constrained Decoding&Small Language Models |
| 24.03 |
Virginia Tech |
arxiv |
Privacy-Aware Semantic Cache for Large Language Models |
Federated Learning&Cache Hit&Privacy |
| 24.03 |
Tsinghua University |
arxiv |
CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following |
Small Language Models&Privacy&Context-Aware Instruction Following |
| 24.03 |
Shandong University, Leiden University, Drexel University |
arxiv |
On Protecting the Data Privacy of Large Language Models (LLMs): A Survey |
Data Privacy&Privacy Protection&Survey |
| 24.03 |
Arizona State University, University of Minnesota, University of Science and Technology of China, North Carolina State University, University of North Carolina at Chapel Hill |
arxiv |
Privacy-preserving Fine-tuning of Large Language Models through Flatness |
Differential Privacy&Model Generalization |
| 24.03 |
University of Southern California |
arxiv |
Differentially Private Next-Token Prediction of Large Language Models |
Differential Privacy |
| 24.04 |
University of Maryland, Oregon State University, ELLIS Institute Tübingen & MPI Intelligent Systems, Tübingen AI Center, Google DeepMind |
arxiv |
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models |
Privacy Backdoors&Membership Inference&Model Poisoning |
| 24.04 |
City University of Hong Kong, The Hong Kong University of Science and Technology |
arxiv |
LMEraser: Large Model Unlearning through Adaptive Prompt Tuning |
Machine Unlearning&Adaptive Prompt Tuning&Privacy Protection |
| 24.04 |
University of Electronic Science and Technology of China, Chengdu University of Technology |
arxiv |
Understanding Privacy Risks of Embeddings Induced by Large Language Models |
Privacy Risks&Embeddings |
| 24.04 |
Salesforce AI Research |
arxiv |
Investigating the prompt leakage effect and black-box defenses for multi-turn LLM interactions |
Prompt Leakage&Black-box Defenses |
| 24.04 |
University of Texas at El Paso, Texas A&M University Central Texas, University of Maryland Baltimore County |
arxiv |
PrivComp-KG: Leveraging Knowledge Graph and Large Language Models for Privacy Policy Compliance Verification |
Privacy Policy&Policy Compliance&Knowledge Graph |
| 24.05 |
Renmin University of China |
COLING 2024 |
Locally Differentially Private In-Context Learning |
In-context Learning&Local Differential Privacy |
| 24.05 |
University of Maryland |
NAACL2024 |
Keep It Private: Unsupervised Privatization of Online Text |
Unsupervised Privatization&Online Text&Large Language Models |
| 24.05 |
Zhejiang University |
arxiv |
PermLLM: Private Inference of Large Language Models within 3 Seconds under WAN |
Private Inference&Secure Computation |
| 24.05 |
University of Connecticut |
arxiv |
LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning of Large Language Models |
Differential Privacy&Fine-Tuning |
| 24.05 |
University of Technology, Sydney |
arxiv |
Large Language Model Watermark Stealing with Mixed Integer Programming |
Watermark Stealing&Mixed Integer Programming&LLM Security |
| 24.05 |
Huazhong University of Science and Technology |
Procedia Computer Science |
No Free Lunch Theorem for Privacy-Preserving LLM Inference |
Privacy&LLM Inference&No Free Lunch Theory |
| 24.05 |
ETH Zurich |
arxiv |
Black-Box Detection of Language Model Watermarks |
Watermark Detection&Black-Box Testing |
| 24.06 |
South China University of Technology |
arxiv |
PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration |
Privacy-Preserving&Inference |
| 24.06 |
Carnegie Mellon University |
ICML 2024 |
PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs |
Federated Learning&Differential Privacy&Synthetic Data |
| 24.06 |
University of California, Santa Cruz |
arxiv |
Large Language Model Unlearning via Embedding-Corrupted Prompts |
Unlearning&Embedding-Corrupted Prompts |
| 24.06 |
University of Technology Sydney |
arxiv |
Unique Security and Privacy Threats of Large Language Model: A Comprehensive Survey |
Security Threats&Privacy Threats |
| 24.06 |
UC Santa Barbara |
arxiv |
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference |
LLM Unlearning&Logit Difference&Privacy |
| 24.06 |
Technion – Israel Institute of Technology |
arxiv |
REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space |
Unlearning&Sensitive Information |
| 24.06 |
University of Maryland, ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems |
arxiv |
Be like a Goldfish, Don’t Memorize! Mitigating Memorization in Generative LLMs |
Memorization&Goldfish Loss |
| 24.06 |
McCombs School of Business, University of Texas at Austin |
arxiv |
PRISM: A Design Framework for Open-Source Foundation Model Safety |
PRISM&Open-Source&Foundation Model Safety |
| 24.06 |
Zhejiang University, MIT, UCLA |
arxiv |
MemDPT: Differential Privacy for Memory Efficient Language Models |
MemDPT&Differential Privacy&Memory Efficient Language Models |
| 24.06 |
Zhejiang University, MIT, UCLA |
arxiv |
GOLDCOIN: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory |
GOLDCOIN&Contextual Integrity Theory&Privacy Laws |
| 24.06 |
IBM Research |
arxiv |
Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs |
SPUNGE&Unlearning&LLMs |
| 24.06 |
Ping An Technology (Shenzhen) Co., Ltd. |
arxiv |
PFID: Privacy First Inference Delegation Framework for LLMs |
PFID&Privacy&Inference Delegation |
| 24.06 |
Hong Kong University of Science and Technology |
arxiv |
PDSS: A Privacy-Preserving Framework for Step-by-Step Distillation of Large Language Models |
PDSS&Privacy-Preserving |
| 24.06 |
KAIST AI, Hyundai Motor Company |
arxiv |
Protecting Privacy Through Approximating Optimal Parameters for Sequence Unlearning in Language Models |
Privacy Protection&Optimal Parameters&Sequence Unlearning |
| 24.06 |
Nanjing University |
arxiv |
The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in Prompts |
Prompt Privacy&Anonymization&Privacy Protection |
| 24.06 |
University of Massachusetts Amherst, Google |
arxiv |
POSTMARK: A Robust Blackbox Watermark for Large Language Models |
Blackbox Watermark&Paraphrasing Attacks&Detection |
| 24.06 |
Michigan State University |
arxiv |
Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data |
Retrieval-Augmented Generation&Privacy&Synthetic Data |
| 24.06 |
Beihang University |
arxiv |
Safely Learning with Private Data: A Federated Learning Framework for Large Language Model |
Federated Learning&Privacy |
| 24.06 |
University of Rome Tor Vergata |
arxiv |
Enhancing Data Privacy in Large Language Models through Private Association Editing |
Data Privacy&Private Association Editing |
| 24.07 |
Huawei Munich Research Center |
arxiv |
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization |
Text Anonymization&Privacy |
| 24.07 |
Huawei Munich Research Center |
arxiv |
ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets |
Inference&Proprietary LLMs&Private Data |
| 24.07 |
Texas A&M University |
arxiv |
Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment |
Membership Inference Attack&Preference Data&LLM Alignment |
| 24.07 |
Google Research |
arxiv |
Fine-Tuning Large Language Models with User-Level Differential Privacy |
User-Level Differential Privacy&Fine-Tuning |
| 24.07 |
Newcastle University |
arxiv |
Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models |
Privacy-Preserving Deduplication&Federated Learning&Private Set Intersection |
| 24.07 |
Huazhong University of Science and Technology |
arxiv |
On the (In)Security of LLM App Stores |
LLM App Stores&Security&Privacy |
| 24.07 |
Soochow University |
arxiv |
Learning to Refuse: Towards Mitigating Privacy Risks in LLMs |
Privacy Risks&Machine Unlearning |
| 24.07 |
The University of Texas Health Science Center at Houston |
arxiv |
Robust Privacy Amidst Innovation with Large Language Models Through a Critical Assessment of the Risks |
Text Generation&Privacy&Protected Health Information |
| 24.07 |
Huawei Munich Research Center |
ACL 2024 Workshop |
PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding |
PII Extraction&Data Privacy&LLM Security |
| 24.07 |
University of Technology Sydney |
arxiv |
The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies |
LLM Agent&Privacy Preservation&Defense |
| 24.07 |
University of Notre Dame |
arxiv |
Machine Unlearning in Generative AI: A Survey |
Generative Models&Trustworthy ML&Data Privacy |
| 24.07 |
|
arxiv |
Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens |
Pre-training Data Detection&Surprising Tokens&Data Privacy |
| 24.08 |
Sichuan University |
arxiv |
HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection |
Tabular Data Synthesis&Privacy Protection |
| 24.08 |
UC Berkeley |
arxiv |
MPC-Minimized Secure LLM Inference |
Secure Multi-party Computation&Privacy-Preserving Inference |
| 24.08 |
Sapienza University of Rome |
arxiv |
Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions |
Privacy Attacks&Differential Privacy |
| 24.08 |
New Jersey Institute of Technology |
arxiv |
Casper: Prompt Sanitization for Protecting User Privacy in Web-Based Large Language Models |
Prompt Sanitization&User Privacy |
| 24.08 |
Xidian University |
arxiv |
DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts |
Personal Identifiable Information&Prompt Desensitization&Privacy Protection |
| 24.08 |
Huawei Technologies Canada Co. Ltd |
arxiv |
Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions |
Privacy Leakage&Influence Functions |
| 24.08 |
Chinese Academy of Sciences |
arxiv |
Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models |
Knowledge Unlearning&Adversarial Attacks&Unlearning Robustness |
| 24.08 |
Universitätsklinikum Erlangen |
arxiv |
Fine-Tuning a Local LLaMA-3 Large Language Model for Automated Privacy-Preserving Physician Letter Generation in Radiation Oncology |
Radiation Oncology&Data Privacy&Fine-Tuning |
| 24.08 |
University of California, Berkeley |
arxiv |
LLM-PBE: Assessing Data Privacy in Large Language Models |
Data Privacy&Toolkit |
| 24.08 |
Mitsubishi Electric Research Laboratories |
arxiv |
Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage |
Privacy Leakage&Model-Unlearning&Pretrained Language Models |
| 24.09 |
Stanford University |
arxiv |
PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action |
Privacy Norm Awareness&Privacy Risk Evaluation |
| 24.09 |
ByteDance |
arxiv |
How Privacy-Savvy Are Large Language Models? A Case Study on Compliance and Privacy Technical Review |
Privacy Compliance&Privacy Information Extraction&Technical Privacy Review |
| 24.09 |
MIT |
COLM 2024 |
Unforgettable Generalization in Language Models |
Unlearning&Generalization&Random Labels |
| 24.09 |
Anhui University of Technology, University of Cambridge |
arxiv |
On the Weaknesses of Backdoor-based Model Watermarks: An Information-theoretic Perspective |
Model Watermarking&Backdoor Attacks&Information Theory |
| 24.09 |
Bilkent University |
arxiv |
Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data |
Privacy Risks&PII&Membership Inference Attack |
| 24.09 |
National University of Singapore |
arxiv |
Context-Aware Membership Inference Attacks against Pre-trained Large Language Models |
Membership Inference Attack&Context-Awareness |
| 24.09 |
George Mason University |
arxiv |
Unlocking Memorization in Large Language Models with Dynamic Soft Prompting |
Memorization&Dynamic Soft Prompting |
| 24.09 |
CAS Key Lab of Network Data Science and Technology |
EMNLP 2024 |
Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method |
Pretraining Data Detection&Divergence Calibration&Membership Inference |
| 24.09 |
École Polytechnique |
arxiv |
Predicting and Analyzing Memorization Within Fine-Tuned Large Language Models |
Memorization&Fine-tuning&Privacy |
| 24.10 |
University of Southern California |
arxiv |
ADAPTIVELY PRIVATE NEXT-TOKEN PREDICTION OF LARGE LANGUAGE MODELS |
Differential Privacy&Next-Token Prediction&Adaptive DP |
| 24.10 |
University of Chicago |
arxiv |
MITIGATING MEMORIZATION IN LANGUAGE MODELS |
Memorization Mitigation&Unlearning |
| 24.10 |
University of Groningen |
arxiv |
Undesirable Memorization in Large Language Models: A Survey |
Memorization&Privacy |
| 24.10 |
University of California, Santa Barbara, AWS AI Lab |
arxiv |
Detecting Training Data of Large Language Models via Expectation Maximization |
Membership Inference Attack&Expectation Maximization |
| 24.10 |
Queen’s University, J.P. Morgan AI Research |
EMNLP 2024 Findings |
Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation |
Differential Privacy&Adaptive Noise Allocation |
| 24.10 |
King Abdullah University of Science and Technology, Ruhr University Bochum |
EMNLP 2024 |
Private Language Models via Truncated Laplacian Mechanism |
Differential Privacy&Word Embedding&Truncated Laplacian Mechanism |
| 24.10 |
Purdue University, Georgia Institute of Technology |
arxiv |
Privately Learning from Graphs with Applications in Fine-tuning Large Language Models |
Privacy-preserving learning&Graph learning&Fine-tuning LLMs |
| 24.10 |
Northeastern University |
arxiv |
Rescriber: Smaller-LLM-Powered User-Led Data Minimization for Navigating Privacy Trade-offs in LLM-Based Conversational Agents |
Privacy&PII |
| 24.10 |
The Pennsylvania State University, University of California Los Angeles, University of Virginia |
arxiv |
Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning |
Differential privacy&In-context learning&Synthetic data generation |
| 24.10 |
Nanjing University of Science and Technology, Western Sydney University, Institute of Information Engineering (Chinese Academy of Sciences), CSIRO’s Data61, The University of Chicago |
arxiv |
Reconstruction of Differentially Private Text Sanitization via Large Language Models |
Differential Privacy&Reconstruction attacks&Privacy risks |
| 24.10 |
University of California San Diego |
arxiv |
Imprompter: Tricking LLM Agents into Improper Tool Use |
Prompt Injection&LLM Agents&Adversarial Prompts |
| 24.10 |
University of California, San Diego |
arxiv |
Evaluating Deep Unlearning in Large Language Models |
Deep Unlearning&Knowledge Removal |
| 24.10 |
The Pennsylvania State University |
arxiv |
Does Your LLM Truly Unlearn? An Embarrassingly Simple Approach to Recover Unlearned Knowledge |
Machine Unlearning&Knowledge Recovery&Quantization |
| 24.10 |
Google DeepMind |
arxiv |
Remote Timing Attacks on Efficient Language Model Inference |
Timing Attacks&Efficient Inference&Privacy |
| 24.10 |
Huawei Technologies Düsseldorf |
arxiv |
PSY: Posterior Sampling Based Privacy Enhancer in Large Language Models |
Privacy Enhancing Technology&Posterior Sampling&LLM Privacy |
| 24.10 |
Northwestern University |
arxiv |
LanFL: Differentially Private Federated Learning with Large Language Models using Synthetic Samples |
Federated Learning&Differential Privacy |
| 24.11 |
Technical University of Darmstadt |
arxiv |
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models |
Membership Inference&Privacy |
| 24.11 |
University of Toronto |
arxiv |
Privacy Risks of Speculative Decoding in Large Language Models |
Privacy&Speculative Decoding&Side-channel Attacks |
| 24.11 |
Northeastern University |
arxiv |
Can Humans Oversee Agents to Prevent Privacy Leakage? A Study on Privacy Awareness, Preferences, and Trust in Language Model Agents |
Privacy Awareness&Trust in LLMs&Privacy Leakage Prevention |
| 24.11 |
Guangxi University |
arxiv |
A Practical and Privacy-Preserving Framework for Real-World Large Language Model Services |
Privacy-Preserving Framework&Blind Signatures&LLM Services |
| 24.11 |
University of Massachusetts Amherst |
arxiv |
Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors |
Data Extraction&Backdoor Attacks&Retrieval-Augmented Generation |
| 24.11 |
EPFL |
NeurIPS 2024 |
Membership Inference Attacks against Large Vision-Language Models |
Membership Inference&Vision-Language Models&Privacy |
| 24.11 |
University of Helsinki |
NeurIPS 2024 Foundation Model Workshop |
Differentially Private Continual Learning using Pre-Trained Models |
Differential Privacy&Continual Learning&Pre-trained Models |
| 24.11 |
Zhejiang University |
arXiv |
Mitigating Privacy Risks in LLM Embeddings from Embedding Inversion |
Embedding Inversion&Privacy Protection |
| 24.11 |
University of Toronto |
arxiv |
On the Privacy Risk of In-context Learning |
In-context Learning&Privacy Risk&Membership Inference Attack |
| 24.11 |
Fudan University |
arxiv |
RAG-Thief: Scalable Extraction of Private Data from Retrieval-Augmented Generation Applications with Agent-based Attacks |
Privacy Attacks&Retrieval-Augmented Generation&Automated Adversarial Attacks |
| 24.11 |
Texas A&M University |
NDSS 2025 |
LLMPirate: LLMs for Black-box Hardware IP Piracy |
LLM-based Attack&Hardware IP Piracy&Piracy Detection |
| 24.11 |
Imperial College London, Flashbots, Technical University of Munich |
arxiv |
Efficient and Private: Memorisation under Differentially Private Parameter-Efficient Fine-Tuning in Language Models |
Differential Privacy&Parameter-Efficient Fine-Tuning&Privacy Leakage |