Pith. sign in

REVIEW 5 cited by

Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.09827 v2 pith:JP4XJRFC submitted 2023-11-16 cs.CL

classification cs.CL
keywords cognitivellmsoverloadjailbreakmodelattacksattackharmful
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after safety alignment. In this paper, we investigate a novel category of jailbreak attacks specifically designed to target the cognitive structure and processes of LLMs. Specifically, we analyze the safety vulnerability of LLMs in the face of (1) multilingual cognitive overload, (2) veiled expression, and (3) effect-to-cause reasoning. Different from previous jailbreak attacks, our proposed cognitive overload is a black-box attack with no need for knowledge of model architecture or access to model weights. Experiments conducted on AdvBench and MasterKey reveal that various LLMs, including both popular open-source model Llama 2 and the proprietary model ChatGPT, can be compromised through cognitive overload. Motivated by cognitive psychology work on managing cognitive load, we further investigate defending cognitive overload attack from two perspectives. Empirical studies show that our cognitive overload from three perspectives can jailbreak all studied LLMs successfully, while existing defense strategies can hardly mitigate the caused malicious uses effectively.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

    cs.CR 2025-08 conditional novelty 6.0 of 10

    ASTRA is an automated red-teaming agent that uses knowledge-graph-guided spatial and temporal probing to find 11-66% more safety violations in AI coding assistants than existing tools.

  2. Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

    cs.CL 2025-08 reject novelty 5.0 of 10

    Sparse autoencoder activation perturbation (SFPF) applied on top of existing jailbreak prompts raises attack success rate on Qwen3-32B, but with no defense evaluation and weak reproducibility.

  3. Towards terahertz nanomechanics

    physics.app-ph 2025-08 unverdicted novelty 5.0 of 10

    Suspended Lamb-wave resonators in lithium niobate films thinned from 300 nm to 67 nm reach 220 GHz, doubling the prior record.

  4. InfoFlood: Jailbreaking Large Language Models with Information Overload

    cs.CR 2025-06 conditional novelty 5.0 of 10

    InfoFlood claims near-perfect jailbreak success on four frontier LLMs by rewriting harmful queries into verbose academic prose with fake citations, past-tense framing, and ethical disclaimers, without adversarial suffixes.

  5. Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems

    cs.CR 2025-07 reject novelty 3.0 of 10

    Multi-stage prompt inference attacks against enterprise LLMs are formalized and defenses are proposed, but the preprint gives no reproducible evidence for its central claims.

Pith tools