会员服务
Cross-Silo De-Anonymization Under Local Differential Privacy: Threat Model, Phase Transition, and Coordination Necessity
Arxiv
0+阅读 · 6月15日
Clinically Grounded Privacy Evaluation of Medical LMs
Arxiv
0+阅读 · 6月8日
Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
Arxiv
0+阅读 · 4月14日
The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Matter
The Pragmatic Frames of Spurious Correlations in Machine Learning: Interpreting How and Why They Matter
Arxiv
0+阅读 · 5月4日
Examining Risks in the AI Companion Application Ecosystem
Arxiv
0+阅读 · 3月13日
RobPI: Robust Private Inference against Malicious Client
Arxiv
0+阅读 · 2月23日
Backdooring Bias in Large Language Models
Arxiv
0+阅读 · 2月13日
"These cameras are just like the Eye of Sauron": A Sociotechnical Threat Model for AI-Driven Smart Home Devices as Perceived by UK-Based Domestic Workers
Arxiv
0+阅读 · 2月9日
Differential Privacy Analysis of Decentralized Gossip Averaging under Varying Threat Models
Arxiv
0+阅读 · 2月5日
Byzantine Machine Learning: MultiKrum and an optimal notion of robustness
Arxiv
0+阅读 · 2月3日
Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments
Arxiv
0+阅读 · 1月31日
Position: 3D Gaussian Splatting Watermarking Should Be Scenario-Driven and Threat-Model Explicit
Arxiv
0+阅读 · 2月1日
Stealthy Poisoning Attacks Bypass Defenses in Regression Settings
Arxiv
0+阅读 · 1月29日
David vs. Goliath: Verifiable Agent-to-Agent Jailbreaking via Reinforcement Learning
Arxiv
0+阅读 · 2月2日
Abusing the Internet of Medical Things: Evaluating Threat Models and Forensic Readiness for Multi-Vector Attacks on Connected Healthcare Devices
Arxiv
0+阅读 · 1月18日
参考链接
微信扫码咨询专知VIP会员
Top