Tag: adversarial attacks
Browse our exclusive articles!
Jailbreak Scaling Laws in Large Language Models Explained
Explore how adversarial attacks cause polynomial to exponential growth in jailbreak success rates of large language models, impacting AI safety.
Red-Teaming Web-Augmented Large Language Models Safely
Explore CREST-Search, a red-teaming framework to identify and mitigate risks in web-augmented large language models for safer AI search results.
Clean-Label Backdoor Attacks on Graph Neural Networks
Explore BA-Logic, a novel method to poison inner prediction logic of GNNs for effective clean-label backdoor attacks in machine learning security.
XFED: Non-Collusive Model Poisoning Attack on Federated Learning
Discover XFED, a non-collusive model poisoning attack that bypasses defenses in federated learning without attacker coordination.
Mosaic: Advanced Multimodal Jailbreak for Closed-Source VLMs
Discover Mosaic, a cutting-edge multimodal jailbreak method enhancing attacks on closed-source VLMs using multi-view ensemble optimization.