会员服务
Cert-SSBD: Certified Backdoor Defense with Sample-Specific Smoothing Noises
Arxiv
0+阅读 · 2月19日
BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning
Arxiv
0+阅读 · 2月19日
Watch Out for the Lifespan: Evaluating Backdoor Attacks Against Federated Model Adaptation
Arxiv
0+阅读 · 2月18日
Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning
Arxiv
0+阅读 · 2月16日
Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning
Arxiv
0+阅读 · 2月9日
Backdoor Attacks on Contrastive Continual Learning for IoT Systems
Arxiv
0+阅读 · 2月13日
Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation
Arxiv
0+阅读 · 2月11日
Defending the Edge: Representative-Attention Defense against Backdoor Attacks in Federated Learning
Arxiv
0+阅读 · 2月12日
BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
Arxiv
0+阅读 · 2月6日
BadSNN: Backdoor Attacks on Spiking Neural Networks via Adversarial Spiking Neuron
Arxiv
0+阅读 · 2月6日
Backdooring Bias in Large Language Models
Arxiv
0+阅读 · 2月13日
Semantic-level Backdoor Attack against Text-to-Image Diffusion Models
Arxiv
0+阅读 · 2月3日
BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models
Arxiv
0+阅读 · 2月5日
Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement Learning
Arxiv
0+阅读 · 2月4日
Inference-Time Backdoors via Hidden Instructions in LLM Chat Templates
Arxiv
0+阅读 · 2月4日
参考链接
微信扫码咨询专知VIP会员
Top