AI Paper Atlas

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

Learning to Lie: Adversarial Attacks on Human-AI Teams and LLMs

Abed K. Musaffar, Anand Gokhale, Sirui Zeng, Rasta Tadayon, Xifeng Yan, Ambuj Singh, Francesco Bullo

ICLR 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial prompts for language 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
use cognitive-model MBRL attacker (lies) in last 15 roundshuman-AI teams · trivia team scorecumulative score: 15% reductionHurt
use MLP-model MBRL attacker (lies) in last 15 roundshuman-AI teams · trivia team scorecumulative score: 24% reductionHurt
use MLP attacker instead of cognitive attackerMBRL attack · trivia team scoreteam score: p < 0.05Improved
cognitive-model attack versus no-attackMBRL attack · trivia team scoreteam score: p = 0.12No clear effect
add current performance (c.p.) to influence models (ablation)cognitive and MLP models · score predictionMSEImproved
add current performance (c.p.) to influence models (ablation)influence matrix prediction models · influence matrix predictionMSENo clear effect
vary attacker window size from 0 to 24 rounds (ablation)MLP and cognitive attacker · simulated cumulative final errorcumulative final errorNo clear effect
add chat logs to LLM input (ablation)ChatGPT 4o-mini influence allocation · influence allocationperformanceImproved
add full performance history to LLM input (ablation)ChatGPT 4o-mini influence allocation · influence allocationperformanceNo clear effect
use chain-of-thought reasoning LLMs (o3-mini, DeepSeek-R1) versus non-reasoningLLM team members · influence allocation under attackperformanceMixed

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