Privacy in ML
Privacy-preserving machine learning
Related Topics (Ethics & Safety)
Top Papers
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
Chongyu Fan, Jiancheng Liu, Yihua Zhang et al.
Fast Machine Unlearning without Retraining through Selective Synaptic Dampening
Jack Foster, Stefan Schoepf, Alexandra Brintrup
Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
Niloofar Mireshghallah, Hyunwoo Kim, Xuhui Zhou et al.
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
Weijia Shi, Jaechan Lee, Yangsibo Huang et al.
EIA: ENVIRONMENTAL INJECTION ATTACK ON GENERALIST WEB AGENTS FOR PRIVACY LEAKAGE
Zeyi Liao, Lingbo Mo, Chejian Xu et al.
AI Sandbagging: Language Models can Strategically Underperform on Evaluations
Teun van der Weij, Felix Hofstätter, Oliver Jaffe et al.
Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
Chongyu Fan, Jiancheng Liu, Alfred Hero et al.
Data Shapley in One Training Run
Jiachen (Tianhao) Wang, Prateek Mittal, Dawn Song et al.
Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios
Jie Xu, Yazhou Ren, Xiaolong Wang et al.
No Prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation
Nimesh Agrawal, Anuj Sirohi, Sandeep Kumar et al.
SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Models
Feifei Wang, Zhentao Tan, Tianyi Wei et al.
DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection
Yuhao Sun, Lingyun Yu, Hongtao Xie et al.
Persistent Pre-training Poisoning of LLMs
Yiming Zhang, Javier Rando, Ivan Evtimov et al.
AA-CLIP: Enhancing Zero-Shot Anomaly Detection via Anomaly-Aware CLIP
wenxin ma, Xu Zhang, Qingsong Yao et al.
On the Relation between Trainability and Dequantization of Variational Quantum Learning Models
Elies Gil-Fuster, Casper Gyurik, Adrian Perez-Salinas et al.
Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It
Adam Lilja, Junsheng Fu, Erik Stenborg et al.
Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
Zhihe Yang, Xufang Luo, Dongqi Han et al.
Machine Unlearning Fails to Remove Data Poisoning Attacks
Martin Pawelczyk, Jimmy Di, Yiwei Lu et al.
A Closer Look at Machine Unlearning for Large Language Models
Xiaojian Yuan, Tianyu Pang, Chao Du et al.
Generalization Analysis of Machine Learning Algorithms via the Worst-Case Data-Generating Probability Measure
Xinying Zou, Samir Perlaza, Inaki Esnaola et al.
Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
Zhaowei Zhu, Jialu Wang, Hao Cheng et al.
T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation
Lijun Li, Zhelun Shi, Xuhao Hu et al.
Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning
Somnath Basu Roy Chowdhury, Krzysztof Choromanski, Arijit Sehanobish et al.
PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees
Chulin Xie, De-An Huang, Wenda Chu et al.
CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG
Boyi Deng, Wenjie Wang, Fengbin Zhu et al.
Encryption-Friendly LLM Architecture
Donghwan Rho, Taeseong Kim, Minje Park et al.
Progressive Poisoned Data Isolation for Training-Time Backdoor Defense
Yiming Chen, Haiwei Wu, Jiantao Zhou
Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model
Tudor Cebere, Aurélien Bellet, Nicolas Papernot
The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense
Yangyang Guo, Fangkai Jiao, Liqiang Nie et al.
Position: Editing Large Language Models Poses Serious Safety Risks
Paul Youssef, Zhixue Zhao, Daniel Braun et al.
IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
Yiren Song, Pei Yang, Hai Ci et al.
MERGE: Fast Private Text Generation
Zi Liang, Pinghui Wang, Ruofei Zhang et al.
LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models
Lukas Helff, Felix Friedrich, Manuel Brack et al.
Regroup Median Loss for Combating Label Noise
Authors: Fengpeng Li, Kemou Li, Jinyu Tian et al.
Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
Yingzi Ma, Jiongxiao Wang, Fei Wang et al.
Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
Jinluan Yang, Anke Tang, Didi Zhu et al.
Backdoor Cleaning without External Guidance in MLLM Fine-tuning
Xuankun Rong, Wenke Huang, Jian Liang et al.
A Generalized Shuffle Framework for Privacy Amplification: Strengthening Privacy Guarantees and Enhancing Utility
Chen E, Yang Cao, Ge Yifei
Minimum-Norm Interpolation Under Covariate Shift
Neil Mallinar, Austin Zane, Spencer Frei et al.
SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining
Pei-Kai Huang, Jun-Xiong Chong, Cheng-Hsuan Chiang et al.
DP-SGD Without Clipping: The Lipschitz Neural Network Way
Louis Béthune, Thomas Massena, Thibaut Boissin et al.
Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models
Thomas Zollo, Todd Morrill, Zhun Deng et al.
Privacy-Preserving Optics for Enhancing Protection in Face De-Identification
Jhon Lopez, Carlos Hinojosa, Henry Arguello et al.
Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework
Maresa Schröder, Dennis Frauen, Stefan Feuerriegel
Emerging Property of Masked Token for Effective Pre-training
Hyesong Choi, Hunsang Lee, Seyoung Joung et al.
Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses
David Glukhov, Ziwen Han, I Shumailov et al.
Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
Siqiao Mu, Diego Klabjan
Poincaré Differential Privacy for Hierarchy-Aware Graph Embedding
Yuecen Wei, Haonan Yuan, Xingcheng Fu et al.
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
Yangsibo Huang, Daogao Liu, Lynn Chua et al.
$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
Jin Zhou, Kaiwen Wang, Jonathan Chang et al.
RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
jingnan zheng, Xiangtian Ji, Yijun Lu et al.
Synthesizing Privacy-Preserving Text Data via Finetuning *without* Finetuning Billion-Scale LLMs
Bowen Tan, Zheng Xu, Eric Xing et al.
Scaling Laws for Differentially Private Language Models
Ryan McKenna, Yangsibo Huang, Amer Sinha et al.
Multi-Dimensional Fair Federated Learning
Cong Su, Guoxian Yu, Jun Wang et al.
Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data Poisoning
Wassim Bouaziz, Nicolas Usunier, El-Mahdi El-Mhamdi
On Harmonizing Implicit Subpopulations
Feng Hong, Jiangchao Yao, YUEMING LYU et al.
SLIM: Spuriousness Mitigation with Minimal Human Annotations
Xiwei Xuan, Ziquan Deng, Hsuan-Tien Lin et al.
Differentially Private Steering for Large Language Model Alignment
Anmol Goel, Yaxi Hu, Iryna Gurevych et al.
Steganographic Passport: An Owner and User Verifiable Credential for Deep Model IP Protection Without Retraining
Qi Cui, Ruohan Meng, Chaohui Xu et al.
Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
Tianchun Wang, Yuanzhou Chen, Zichuan Liu et al.
Privacy Attacks on Image AutoRegressive Models
Antoni Kowalczuk, Jan Dubiński, Franziska Boenisch et al.
PPIDSG: A Privacy-Preserving Image Distribution Sharing Scheme with GAN in Federated Learning
Yuting Ma, Yuanzhi Yao, Xiaohua Xu
Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment
Alvi Md Ishmam, Chris Thomas
Privacy amplification by random allocation
Moshe Shenfeld, Vitaly Feldman
From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
Yang Li, Qiang Sheng, Yehan Yang et al.
Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures
Sayanton Vhaduri Dibbo, Adam Breuer, Juston Moore et al.
SEMU: Singular Value Decomposition for Efficient Machine Unlearning
Marcin Sendera, Łukasz Struski, Kamil Książek et al.
Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion
Tianyuan Zou, Yang Liu, Peng Li et al.
Robustness Auditing for Linear Regression: To Singularity and Beyond
Ittai Rubinstein, Samuel Hopkins
OpticalDR: A Deep Optical Imaging Model for Privacy-Protective Depression Recognition
Yuchen Pan, Junjun Jiang, Kui Jiang et al.
Position: The Artificial Intelligence and Machine Learning Community Should Adopt a More Transparent and Regulated Peer Review Process
Jing Yang
Mask in the Mirror: Implicit Sparsification
Tom Jacobs, Rebekka Burkholz
Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
Chen Chen, Daochang Liu, Mubarak Shah et al.
Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks
Tianqu Zhuang, Hongyao Yu, Yixiang Qiu et al.
The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
Blaise Delattre, Alexandre Araujo, Quentin Barthélemy et al.
Data-Free Hard-Label Robustness Stealing Attack
Xiaojian Yuan, Kejiang Chen, Wen Huang et al.
Differentially Private Federated Learning with Time-Adaptive Privacy Spending
Shahrzad Kianidehkordi, Nupur Kulkarni, Adam Dziedzic et al.
Strategic Classification With Externalities
Safwan Hossain, Evi Micha, Yiling Chen et al.
Protect Your Score: Contact-Tracing with Differential Privacy Guarantees
Rob Romijnders, Christos Louizos, Yuki Asano et al.
Understanding Generalization in Quantum Machine Learning with Margins
TAK HUR, Daniel Kyungdeock Park
Hessian-Free Online Certified Unlearning
Xinbao Qiao, Meng Zhang, Ming Tang et al.
Near-Optimal Resilient Aggregation Rules for Distributed Learning Using 1-Center and 1-Mean Clustering with Outliers
Yuhao Yi, Ronghui You, Hong Liu et al.
Learning Safe Action Models with Partial Observability
Hai Le, Brendan Juba, Roni Stern
Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
Yufei Gu, Xiaoqing Zheng, Tomaso Aste
Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
Fengyu Gao, Ruida Zhou, Tianhao Wang et al.
Towards Trustworthy Federated Learning with Untrusted Participants
Youssef Allouah, Rachid Guerraoui, John Stephan
Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarios
xihong yang, Siwei Wang, Fangdi Wang et al.
A Generic Framework for Conformal Fairness
Aditya Vadlamani, Anutam Srinivasan, Pranav Maneriker et al.
Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models
Linh Tran, Wei Sun, Stacy Patterson et al.
SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness
Sangamesh Kodge, Deepak Ravikumar, Gobinda Saha et al.
DF-MIA: A Distribution-Free Membership Inference Attack on Fine-Tuned Large Language Models
Zhiheng Huang, Yannan Liu, Daojing He et al.
X-Hacking: The Threat of Misguided AutoML
Rahul Sharma, Sumantrak Mukherjee, Andrea Šipka et al.
How Far Are We from True Unlearnability?
Kai Ye, Liangcai Su, Chenxiong Qian
Prediction Exposes Your Face: Black-box Model Inversion via Prediction Alignment
Yufan Liu, Wanqian Zhang, Dayan Wu et al.
Personalized Privacy Protection Mask Against Unauthorized Facial Recognition
Ka Ho Chow, Sihao Hu, Tiansheng Huang et al.
DCT-CryptoNets: Scaling Private Inference in the Frequency Domain
Arjun Roy, Kaushik Roy
Towards Establishing Guaranteed Error for Learned Database Operations
Sepanta Zeighami, Cyrus Shahabi
Differential Privacy Under Class Imbalance: Methods and Empirical Insights
Lucas Rosenblatt, Yuliia Lut, Ethan Turok et al.
ExcluIR: Exclusionary Neural Information Retrieval
Wenhao Zhang, Mengqi Zhang, Shiguang Wu et al.
Bayesian Low-Rank Learning (Bella): A Practical Approach to Bayesian Neural Networks
Bao Gia Doan, Afshar Shamsi, Xiao-Yu Guo et al.