TGViewer
ML&|Sec Feed ML&|Sec Feed @mlsecfeed · 1.38K subscribers
Post #2044 199

Forwarded from CyberSecurityTechnologies

TrojAI_Final_Report.pdf14.2 MB
#Analytics
#Research
#MLSecOps
"Trojans in Artificial Intelligence. Final Report",
IARPA, Jan. 2026.

// This report synthesizes the TrojAI program's key findings, including methodologies for detection through weight analysis and trigger inversion, as well as approaches for mitigating Trojan risks in deployed models. Comprehensive test and evaluation results highlight detector performance, sensitivity, and the prevalence of "natural" Trojans. The report concludes with lessons learned and recommendations for advancing AI security research
More from @mlsecfeed
  1. Oct 6, 2026https://huggingface.co/spaces/AlexWortega/openjev чат а го накидаем лайков жеска, я чет за…
  2. Oct 6, 2026Bitdefender внезапно выпустила свой бесплатный антивирус для ИИ-агентов 💪 AI Guardian сле…
  3. Oct 5, 2026https://poloclub.github.io/transformer-explainer/
  4. Oct 4, 2026GLM-5.3 без цензуры: вышел EXL3-квант на 3 бита На Hugging Face появилась uncensored-верси…
  5. Oct 3, 2026На Хабре вышла статья о том, что ИИ изменил в кибератаках от нашей Red Team команды (tl;dr…
  6. Oct 2, 2026Cloudflare тоже сделали свои версии Jev Они выпустили Clef и Clef-flash, две открытые deci…
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →