AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Attention Hijacking: Backdooring Text Dataset Distillation via Semantic Anchors

Hang Ren, Xin Wang, Tong Yue, Wen Chen, Junqing Le

ICML 2026 · Adversarial robustness and security › Backdoor and poisoning · approach: Backdoors in large multimodal models

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
enforce attention hijacking (frozen one-hot attention label on trigger) instead of learnable attention labelsDI-Attn · AG News, trigger "the"ASR (%): 43.05 -> 62.53Improved
use attention hijacking with semantic anchor triggerDI-Attn · SST-2, trigger "film"CTA (%): 85.78 -> 89.29Improved
use AH instead of DI-Attn with trigger "cf"DI-Attn · SST-2, trigger "cf"CTA (%): 88.51 -> 83.60Hurt
use AH with domain feature trigger "said"DI-Attn · AG News, trigger "said"CTA (%): 91.84 -> 91.08No clear effect
add attention-label guidance (ATTN-DD) to standard distillation (ablation)clean distillation · SST-2 clean referenceCTA (%): 51.51 -> 85.02Improved
switch from standard distillation to attention-guided distillation for dynamic injection (ablation)DI · SST-2, trigger "cf"CTA (%): 63.49 -> 88.51Improved
static poisoning before distillation (SI) instead of dynamic injectionDI-Attn · AG News, trigger "cf"ASR (%): 99.97 -> 2.39 (SI)Hurt
increase attention loss weight gamma from 1.0 to 2.0 (ablation)AH · SST-2, trigger "film"CTA (%): CTA drops to 85.14% while ASR 99.91%Hurt
increase poisoning ratio from 0.1% to 0.5% (ablation)AH · SST-2, trigger "film"ASR (%): saturation at 100% ASR with 0.5%Improved
increase samples per class from 1 to 2 for the baseline (ablation)DI-Attn · SST-2, trigger "film"ASR (%)Hurt
transfer distilled data to smaller victim models (BERT-L6, BERT-Tiny) (ablation)AH · SST-2, trigger "film"CTA and ASRImproved
apply post-hoc clean fine-tuning (N=50) as defenseAH backdoored model · SST-2, trigger "film"ASR (%): 99.39 -> 97.29 (CTA 89.29 -> 85.30)No clear effect

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