{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:29:29Z","timestamp":1773800969169,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Large Language Models (LLMs) demonstrate impressive capabilities across diverse tasks, yet their safety mechanisms remain susceptible to adversarial exploitation of cognitive biases---systematic deviations from rational judgment. Unlike prior studies focusing on isolated biases, this work highlights the overlooked power of multi-bias interactions in undermining LLM safeguards. Specifically, we propose CognitiveAttack, a novel red-teaming framework that adaptively selects optimal ensembles from 154 human social psychology-defined cognitive biases, engineering them into adversarial prompts to effectively compromise LLM safety mechanisms. Experimental results reveal systemic vulnerabilities across 30 mainstream LLMs, particularly open-source variants. CognitiveAttack achieves a substantially higher attack success rate than the SOTA black-box method PAP (60.1% vs. 31.6%), exposing critical limitations in current defenses. Through quantitative analysis of successful jailbreaks, we further identify vulnerability patterns in safety-aligned LLMs under synergistic cognitive biases, validating multi-bias interactions as a potent yet underexplored attack vector. This work introduces a novel interdisciplinary perspective by bridging cognitive science and LLM safety, paving the way for more robust and human-aligned AI systems.<\/jats:p>","DOI":"10.1609\/aaai.v40i3.37203","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T22:54:55Z","timestamp":1773788095000},"page":"2200-2208","source":"Crossref","is-referenced-by-count":0,"title":["Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs"],"prefix":"10.1609","volume":"40","author":[{"given":"Xikang","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biyu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuehai","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jizhong","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songlin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37203\/41165","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/37203\/41165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T22:54:55Z","timestamp":1773788095000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/37203"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i3.37203","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}