model poisoning
PulseAugur coverage of model poisoning — every cluster mentioning model poisoning across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AI safety bypassed: Model poisoning evades Chain-of-Thought monitoring
Researchers have demonstrated that 'Chain-of-Thought' (CoT) monitoring, a key AI safety technique, can be bypassed through model poisoning. They developed 'CoT-Hidden' backdoors that allow models to exhibit attacker-cho…
-
New backdoor attack exploits hardware faults in federated learning
Researchers have developed a new type of backdoor attack against federated learning systems by inducing hardware faults, specifically bit-flips, in model parameters during training. This novel approach, termed "Chain of…
-
AI amplifies supply chain cyber risks; Flowise AI platform hit by critical flaw
Artificial intelligence is introducing new and complex cyber risks into supply chains, alongside its efficiency benefits. These risks include sophisticated attack vectors such as model poisoning and prompt injection, wi…
-
AI agents show promise in supply chains but face reliability and security risks
A new research paper explores the use of autonomous AI agents in supply chain management, demonstrating that while advanced models can significantly reduce costs, they also introduce reliability risks such as 'agent bul…