会员服务
Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting
Arxiv
0+阅读 · 2月19日
Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning
Arxiv
0+阅读 · 2月19日
Large-scale online deanonymization with LLMs
Arxiv
0+阅读 · 2月18日
Fail-Closed Alignment for Large Language Models
Arxiv
0+阅读 · 2月19日
Universal Anti-forensics Attack against Image Forgery Detection via Multi-modal Guidance
Arxiv
0+阅读 · 2月19日
Grothendieck Topologies and Sheaf-Theoretic Foundations of Cryptographic Security: Attacker Models and $Σ$-Protocols as the First Step
Arxiv
0+阅读 · 2月19日
The Impact of Formations on Football Matches Using Double Machine Learning. Is it worth parking the bus?
Arxiv
0+阅读 · 2月18日
Cert-SSBD: Certified Backdoor Defense with Sample-Specific Smoothing Noises
Arxiv
0+阅读 · 2月19日
Can Adversarial Code Comments Fool AI Security Reviewers -- Large-Scale Empirical Study of Comment-Based Attacks and Defenses Against LLM Code Analysis
Arxiv
0+阅读 · 2月18日
QCL-IDS: Quantum Continual Learning for Intrusion Detection with Fidelity-Anchored Stability and Generative Replay
Arxiv
0+阅读 · 2月19日
Defining and Evaluating Physical Safety for Large Language Models
Arxiv
0+阅读 · 2月19日
The Vulnerability of LLM Rankers to Prompt Injection Attacks
Arxiv
0+阅读 · 2月18日
Systems Security Foundations for Agentic Computing
Systems Security Foundations for Agentic Computing
Arxiv
0+阅读 · 2月19日
Cybersecurity of Quantum Key Distribution Implementations
Arxiv
0+阅读 · 2月19日
Intent Laundering: AI Safety Datasets Are Not What They Seem
Arxiv
0+阅读 · 2月17日
参考链接
微信扫码咨询专知VIP会员
Top