会员服务
SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration
SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration
Arxiv
0+阅读 · 3月16日
PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
Arxiv
0+阅读 · 3月13日
Purify Once, Edit Freely: Breaking Image Protections under Model Mismatch
Arxiv
0+阅读 · 3月13日
Improved Leakage Abuse Attacks in Searchable Symmetric Encryption with eBPF Monitoring
Arxiv
0+阅读 · 3月7日
PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing
Arxiv
0+阅读 · 2月26日
Stealthy Poisoning Attacks Bypass Defenses in Regression Settings
Arxiv
0+阅读 · 3月2日
Sparsification Under Siege: Dual-Level Defense Against Poisoning in Communication-Efficient Federated Learning
Arxiv
0+阅读 · 2月28日
Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective
Arxiv
0+阅读 · 2月17日
Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening
Arxiv
0+阅读 · 2月6日
Exploring Adversarial Watermarking in Transformer-Based Models: Transferability and Robustness Against Defense Mechanism for Medical Images
Arxiv
0+阅读 · 2月7日
Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
Arxiv
0+阅读 · 2月16日
AirCatch: Effectively tracing advanced tag-based trackers
Arxiv
0+阅读 · 2月7日
TinyGuard:A lightweight Byzantine Defense for Resource-Constrained Federated Learning via Statistical Update Fingerprints
Arxiv
0+阅读 · 2月2日
System Password Security: Attack and Defense Mechanisms
Arxiv
0+阅读 · 2月2日
Safety-Efficacy Trade Off: Robustness against Data-Poisoning
Arxiv
0+阅读 · 1月31日
参考链接
微信扫码咨询专知VIP会员
Top