会员服务
Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation
Arxiv
0+阅读 · 3月17日
Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
Arxiv
0+阅读 · 3月16日
Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights
Arxiv
0+阅读 · 3月13日
Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads
Arxiv
0+阅读 · 3月13日
Prompt Injection Vulnerability of Consensus Generating Applications in Digital Democracy
Arxiv
0+阅读 · 2月28日
On The Fragility of Benchmark Contamination Detection in Reasoning Models
Arxiv
0+阅读 · 3月2日
''I don't want to break it'': An Exploration of Perceived Fragility in Shape-Changing Interfaces
Arxiv
0+阅读 · 3月9日
Blockchain Communication Vulnerabilities
Arxiv
0+阅读 · 3月3日
Opportunities and Challenges of Operating Semi-Autonomous Vehicles: A Layered Vulnerability Perspective
Arxiv
0+阅读 · 3月1日
Evaluating Cooling Center Coverage Using Persistent Homology of a Filtered Witness Complex
Arxiv
0+阅读 · 3月10日
Vulnerability-Amplifying Interaction Loops: a systematic failure mode in AI chatbot mental-health interactions
Arxiv
0+阅读 · 3月9日
Anyone but Him: The Complexity of Precluding an Alternative
Arxiv
0+阅读 · 3月4日
SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
Arxiv
0+阅读 · 2月22日
Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals
Arxiv
0+阅读 · 3月3日
Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards
Arxiv
0+阅读 · 2月22日
参考链接
微信扫码咨询专知VIP会员
Top