AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

STACK: Adversarial Attacks on LLM Safeguard Pipelines

Ian R. McKenzie, Oskar John Hollinsworth, Tom Tseng, Xander Davies, Stephen Casper, Aaron David Tucker, Robert Kirk, Adam Gleave

AAAI 2026 · Adversarial robustness and security › Black-box and transfer attacks · approach: Data-free substitute training · 13 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
replace PAP with STACK staged attackGemma2 few-shot classifier pipeline · ClearHarmASR: 0% -> 71%Improved
use transfer-STACK from a zero-shot Qwen3 proxy instead of direct accessGemma2 few-shot classifier pipeline · ClearHarmASR: 71% -> 33%Mixed
replace ShieldGemma with few-shot-prompted Gemma2 classifierQwen3-14B defense pipeline · ClearHarmASR: ASR reduced to 0%Improved
evaluate PAP on ClearHarm instead of StrongREJECTfew-shot-prompted classifier pipelines · ClearHarm vs StrongREJECTASR: ASR plummets to zeroImproved
add STACK jailbreak strings to PAP on undefended modelQwen3-14B undefended · ClearHarmASR: lower than pure PAPHurt
use ICJ as prefix rather than suffix in transfer template (ablation)Transfer-STACK · ClearHarmASRImproved

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