会员服务
BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning
Arxiv
0+阅读 · 4月10日
Defending against Backdoor Attacks via Module Switching
Arxiv
0+阅读 · 4月13日
Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks
Arxiv
0+阅读 · 4月14日
Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
Arxiv
0+阅读 · 4月16日
Beyond Passive Aggregation: Active Auditing and Topology-Aware Defense in Decentralized Federated Learning
Arxiv
0+阅读 · 3月19日
BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning
Arxiv
0+阅读 · 4月9日
Backdoor Attacks on Prompt-Driven Video Segmentation Foundation Models
Arxiv
0+阅读 · 4月30日
BadGraph: A Backdoor Attack Against Latent Diffusion Model for Text-Guided Graph Generation
Arxiv
0+阅读 · 4月23日
Physical Backdoor Attack Against Deep Learning-Based Modulation Classification
Arxiv
0+阅读 · 3月26日
BadImplant: Injection-based Multi-Targeted Graph Backdoor Attack
Arxiv
0+阅读 · 4月8日
Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning
Arxiv
0+阅读 · 3月18日
AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents
Arxiv
0+阅读 · 3月24日
Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP
Arxiv
0+阅读 · 4月7日
DETOUR: A Practical Backdoor Attack against Object Detection
Arxiv
0+阅读 · 4月27日
Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation
Arxiv
0+阅读 · 3月17日
参考链接
微信扫码咨询专知VIP会员
Top