This paper introduces a fast and efficient post-hoc defense against a type of attack that can bypass safety features in language models, allowing the model to continue functioning but with compromised security. Practitioners caring about model security may be interested in this approach as it can provide an additional layer of protection without requiring significant computational resources.
Firehose
Filtered to tagged “ablation attacks” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
artificial intelligence 87continual learning 32AI 24reinforcement learning 14agentic coding 13AI safety 13open-weight models 13AI agents 10existential risk 9AI ethics 8cybersecurity 8ethics 7language models 7machine learning 7natural language processing 6open-source 6Reinforcement learning 6security 6artificial general intelligence 5Diffusion models 5recursive self-improvement 5robotics 5software development 5Agentic AI 4large language models 4mathematics 4multi-agent systems 4Recursive self-improvement 4agentic AI 3agents 3