会员服务
Adversarial Attacks Leverage Interference Between Features in Superposition
Arxiv
0+阅读 · 6月15日
Tail-Shape Estimation in LLM Evaluation Is Fragile: A Protocol for Diagnosing False Positives
Arxiv
0+阅读 · 6月15日
Cognitive Debt: AI as Intellectual Leverage and the Dynamics of Systemic Fragility
Arxiv
0+阅读 · 6月13日
CmdNeedle: Measuring the Incompleteness of Command Denylists for AI Agents
Arxiv
0+阅读 · 6月14日
How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation
Arxiv
0+阅读 · 6月15日
From ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMs
Arxiv
0+阅读 · 6月14日
The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions
Arxiv
0+阅读 · 6月12日
Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems
Arxiv
0+阅读 · 6月7日
SENTRY: Statistical Reliability Analysis of Vision Transformers Under Soft Errors
Arxiv
0+阅读 · 5月30日
The Human Vulnerabilities & Exploits (HVE) Framework
Arxiv
0+阅读 · 6月8日
FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint
Arxiv
0+阅读 · 6月7日
Backbone is All You Need: Assessing Vulnerabilities of Frozen Foundation Models in Synthetic Image Forensics
Arxiv
0+阅读 · 5月13日
Ev-Trust: An Evolutionarily Stable Trust Mechanism for Decentralized LLM-Based Multi-Agent Service Economies
Arxiv
0+阅读 · 5月31日
Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults
Arxiv
0+阅读 · 6月9日
Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage
Arxiv
0+阅读 · 5月18日
参考链接
微信扫码咨询专知VIP会员
Top