AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

LAMP: Learning Universal Adversarial Perturbations for Multi-Image Tasks via Pre-trained Models

Alvi Md Ishmam, Najibul Haque Sarker, Zaber Ibn Abdul Hakim, Chris Thomas

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness · 1 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 the contagious loss (ablation)LAMP · Mantis-EvalASR (%): 70.32 -> 73.43Improved
add the contagious loss (ablation)LAMP · NLVR2ASR (%): 49.33 -> 52.73Improved
add the contagious loss (ablation)LAMP · BLINKASR (%): 82.64 -> 84.86Improved
add the contagious loss and index-attention suppression to LM+dec+h losses (ablation)LAMP · NLVR2ASR (%): 44.35 -> 52.73Improved
add contagious loss to the first three loss terms (ablation)LAMP · Mantis-Eval, Mantis-CLIPASR (%): 68.66 -> 71.88Improved
add the hidden-state loss to the LM loss (ablation)LAMP · Mantis-Eval, Mantis-CLIPASR (%): 59.55 -> 63.68Improved
add the Hausdorff attention loss to LM + hidden-state losses (ablation)LAMP · Mantis-Eval, Mantis-CLIPASR (%): 63.68 -> 68.66Improved
increase number of universal perturbations from 1 to 2 (ablation)LAMP · Mantis-Eval, Mantis-CLIPASR (%)Improved
use more than 2 perturbations (ablation)LAMP · Mantis-Eval, Mantis-CLIPASR (%)No clear effect
increase perturbation budget beyond 12/255 (ablation)LAMP · multi-image benchmarksASR (%)No clear effect
set contagious and position losses weights to 1.2 instead of all 1 (ablation)LAMP · Mantis-Eval, Mantis-CLIPASR (%): 72.9 -> 73.43No clear effect
add the contagious loss (contamination analysis) (ablation)LAMP · Mantis-EvalASR (%): 61.1 -> 73.4Improved

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