COLM 2026 paper InjecMEM shows a single interaction, with no access to the memory store, can plant an optimized record that is later retrieved and steers a research agent's answers. Retrieve-time filters barely helped.
Academic and industry research shaping the future of AI security, attack, and defence.
COLM 2026 paper InjecMEM shows a single interaction, with no access to the memory store, can plant an optimized record that is later retrieved and steers a research agent's answers. Retrieve-time filters barely helped.
A new benchmark from Shanghai AI Laboratory tests six leading GUI agents against environmental injection attacks embedded in real Android apps. Every agent is vulnerable, attack success rates reach 66.9%, and stronger agents turn out to be more exploitable, not less.
Anthropic and EPFL researchers demonstrate that ideological and action payloads can spread between AI agents through editable system prompt state files, surviving 20-hop chains with no human intervention. One defensive measure stops them almost entirely.
1Password's Off-by-1 Labs tested two frontier AI models against six real CVEs and found that only a quarter of the generated patches fully fixed the vulnerability without introducing new problems. The implications for teams relying on AI-assisted remediation are significant.
Knowledge distillation attacks can transfer and forge the statistical watermarks embedded in LLM outputs, undermining EU AI Act content provenance requirements and attribution-based trust systems before they fully take effect.