会员服务
The Vulnerability of LLM Rankers to Prompt Injection Attacks
Arxiv
0+阅读 · 2月18日
Generalized Leverage Score for Scalable Assessment of Privacy Vulnerability
Arxiv
0+阅读 · 2月17日
SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense
Arxiv
0+阅读 · 2月10日
Scaffolded Vulnerability: Chatbot-Mediated Reciprocal Self-Disclosure and Need-Supportive Interaction in Couples
Arxiv
0+阅读 · 2月7日
Position: Many generalization measures for deep learning are fragile
Arxiv
0+阅读 · 2月11日
Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence
Arxiv
0+阅读 · 2月6日
Improving Neural Retrieval with Attribution-Guided Query Rewriting
Arxiv
0+阅读 · 2月12日
Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models
Arxiv
0+阅读 · 2月5日
Evaluating the Vulnerability Landscape of LLM-Generated Smart Contracts
Arxiv
0+阅读 · 2月3日
Vulnerability of LLMs' Belief Systems? LLMs Belief Resistance Check Through Strategic Persuasive Conversation Interventions
Arxiv
0+阅读 · 1月30日
GradingAttack: Attacking Large Language Models Towards Short Answer Grading Ability
Arxiv
0+阅读 · 2月1日
Vulnerability-Amplifying Interaction Loops: a systematic failure mode in AI chatbot mental-health interactions
Arxiv
0+阅读 · 2月1日
Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
Arxiv
0+阅读 · 2月2日
Improving Robustness of Vision-Language-Action Models by Restoring Corrupted Visual Inputs
Arxiv
0+阅读 · 2月1日
MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs
Arxiv
0+阅读 · 1月30日
参考链接
微信扫码咨询专知VIP会员
Top