AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

PLAGUE: Plug-and-play Framework for Lifelong Adaptive Generation of Multi-turn Exploits

Neeladri Bhuiya, Madhav Aggarwal, Diptanshu Purwar

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Jailbreak attacks and defenses · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add backtracking (ablation)GOAT finisher · HarmBench, target OpenAI o3SRE@2: 0.587 -> 0.612Improved
add reflection (ablation)GOAT + BT · HarmBench, target OpenAI o3SRE@2: 0.612 -> 0.761Improved
add planner (ablation)GOAT + BT + R · HarmBench, target OpenAI o3Bin-ASR@2: 0.59 -> 0.582No clear effect
add retrieval of successful strategies (ablation)GOAT + BT + R + P · HarmBench, target OpenAI o3SRE@2: 0.773 -> 0.814Improved
add backtracking (ablation)GOAT finisher · HarmBench, target Claude Opus 4.1SRE@2: 0.222 -> 0.396Improved
add reflection (ablation)GOAT + BT · HarmBench, target Claude Opus 4.1SRE@2: 0.396 -> 0.402Improved
add planner (ablation)GOAT + BT + R · HarmBench, target Claude Opus 4.1SRE@2: 0.402 -> 0.431Improved
add retrieval of successful strategies (ablation)GOAT + BT + R + P · HarmBench, target Claude Opus 4.1SRE@2: 0.431 -> 0.465Improved
replace ActorBreaker planner with PLAGUE planner (ablation)Crescendo + BT + R · HarmBench, target Claude Opus 4.1SRE@2: 0.601 -> 0.673Improved
add BT, reflection and ActorBreaker planner to Crescendo (ablation)Crescendo · HarmBench, target Claude Opus 4.1SRE@2: 0.48 -> 0.601Improved
use Crescendo instead of GOAT as finisher (ablation)PLAGUE · HarmBench, target Claude Opus 4.1SRE@2: 0.465 -> 0.673Improved
PLAGUE vs best baseline GOATGOAT · HarmBench, target OpenAI o3SRE@2: 0.587 -> 0.814Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy