会员服务
Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning
Arxiv
0+阅读 · 2月19日
Astra: AI Safety, Trust, & Risk Assessment
Arxiv
0+阅读 · 2月19日
Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies
Arxiv
0+阅读 · 2月7日
Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink
Arxiv
0+阅读 · 2月11日
"Create an environment that protects women, rather than selling anxiety!": Participatory Threat Modeling with Chinese Young Women Living Alone
Arxiv
0+阅读 · 2月9日
WebWorld: A Large-Scale World Model for Web Agent Training
Arxiv
0+阅读 · 2月16日
Beyond Permissions: An Empirical Static Analysis of Privacy and Security Risks in Children-Oriented and General-Audience Mobile Apps for Gaming
Arxiv
0+阅读 · 2月11日
Reasoning about Intent for Ambiguous Requests
Arxiv
0+阅读 · 2月13日
GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
Arxiv
0+阅读 · 2月12日
Assessing Cybersecurity Risks and Traffic Impact in Connected Autonomous Vehicles
Arxiv
0+阅读 · 2月14日
CryptoCatch: Cryptomining Hidden Nowhere
Arxiv
0+阅读 · 2月11日
CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models
Arxiv
0+阅读 · 2月5日
ROMAN: Reward-Orchestrated Multi-Head Attention Network for Autonomous Driving System Testing
Arxiv
0+阅读 · 2月5日
VocBulwark: Towards Practical Generative Speech Watermarking via Additional-Parameter Injection
Arxiv
0+阅读 · 1月30日
MoveScanner: Analysis of Security Risks of Move Smart Contracts
Arxiv
0+阅读 · 2月2日
参考链接
微信扫码咨询专知VIP会员
Top