Unveiling the Backdoor’s Suppression Effect for Backdoor Defence

Summary

Researchers report that when a second backdoor is embedded into a deep neural network after an earlier one, the later backdoor suppresses the earlier one. Building on this, they propose Safedoor, a defensive backdoor embedded into suspect models using a small amount of data. Across eight representative backdoor attacks, Safedoor reduces the average attack success rate from 97.3% to 2.2%, while keeping clean-data accuracy high and adding 0.32% to inference time.

Mitigation

Safedoor: intentionally embed a later backdoor (Safedoor) into suspect DNNs that may already be infected, using the proposed efficient embedding algorithm.

Related items

• CriticalCVE-2026-108263: Astron Agent is an agentic workflow platform for building and running AI agents. Prior to 1.1.2, the default workflow coSimilar attack · NVD/CVE Database
• MediumHackers abuse Google Ads, Bing redirects to push Claude ClickFix attacksSimilar attack · BleepingComputer
• LowSocial Engineering AI Agents: The New BEC for 2026Similar attack · Dark Reading
• HighGHSA-cv3g-hj65-pcfh: PraisonAI: Shell command allowlist bypass via find -exec built-in actionSimilar attack · GitHub Advisory Database
• CriticalGHSA-9mp3-24cc-77mg: PraisonAI: AICoder Arbitrary File Write and Command Execution via LLM Tool CallsSimilar attack · GitHub Advisory Database