InfoResearchPeer-reviewedLLM-specific
Adversarial prompt detection via contrastive dual-encoder transformer for zero-day jailbreak defense based on AdverSentinel-LLM model
- Published
- Record updated
Summary
Researchers present AdverSentinel-LLM, an adversarial prompt detector built on a Contrastive Dual-Encoder Transformer (CDET) that flags malicious prompts in real time, including zero-day jailbreaks. The method pairs a Prompt Semantic Encoder with a Threat Pattern Encoder, trained under a supervised contrastive objective, and adds a Dynamic Threat Memory Bank and an Anomaly-Aware Gating Mechanism. On AdvBench, JailbreakBench, ToxicChat and PromptSafety-Bench it reports an F1-score of 0.967, 97.3% detection accuracy and a 94.8% zero-day detection rate.
Topics
Related items
- InfoAnthropic’s record IPO collides with tech’s worst week on Wall Street since 2020Same vendor · CNBC Technology
- InfoAnthropic mathematician claims he used Claude to prove 19th-century Riemann hypothesisSame vendor · The Guardian Technology
- InfoCan Anthropic afford to put safety first?Same vendor · The Verge (AI)
- Info‘I was shaking, crying, having trouble breathing’: the unchartered trauma of breaking up with AI companionsSame vendor · The Guardian Technology
- LowSignal Blocks AI Agents From Reading Private Chats via Screenshots on Android and iOSSame vendor · The Hacker News