Adversa AI publishes October GenAI security resource roundup
Start here
Adversa AI published its monthly roundup of GenAI security resources for October 2026, collecting 38 resources by topic. The attack techniques section includes AKRASIA, a backdoor in reasoning code models (average attack success rate up to 99.34%), InceptionRAG and Micro-Collaborative Poisoning against RAG, and activation-dilution jailbreaks that split harmful requests into subproblems to dilute safety signals. The defenses section covers directions such as CounterSteer, which uses activation steering to suppress indirect prompt injection, and homomorphic encryption.
Generated by AI from reports · Updated 2026-10-13
Progress timeline
- Adversa AIAdversa AI's curated GenAI security resources (October 2026)
Adversa AI releases its October 2026 monthly roundup of GenAI security resources, compiling 38 resources by theme. The attack techniques section includes the reasoning code model backdoor AKRASIA (with average attack success rates up to 99.34%), InceptionRAG and Micro-Collaborative Poisoning against RAG, and activation-dilution jailbreaks that split harmful requests into subproblems to dilute safety signals. The defenses section covers CounterSteer, which suppresses indirect prompt injection using activation steering, the homomorphic encryption guardrail HE-Guardrail, and locating backdoors with sparse autoencoders. The vulnerabilities section documents an access control flaw in the LiteLLM proxy (CVE-2026-35029) and a SafeUnpickler bypass in SGLang (CVE-2026-86793, CVSS 9.8).