paper-with-me

홈 › Papers

Adversarial Manipulation of Reasoning Models using Internal Representations

2025-07-03 · Kureha Yamaguchi, Benjamin Etheridge, Andy Arditi

Reasoning models generate chain-of-thought (CoT) tokens before their final output, but how this affects their vulnerability to jailbreak attacks remains unclear. While traditional language models make refusal decisions at the prompt-response boundary, we find evidence that DeepSeek-R1-Distill-Llama-8B makes these decisions within its CoT generation. We identify a linear direction in activation space during CoT token generation that predicts whether the model will refuse or comply -- termed the "caution" direction because it corresponds to cautious reasoning patterns in the generated text. Ablating this direction from model activations increases harmful compliance, effectively jailbreaking the model. We additionally show that intervening only on CoT token activations suffices to control final outputs, and that incorporating this direction into prompt-based attacks improves success rates. Our findings suggest that the chain-of-thought itself is a promising new target for adversarial manipulation in reasoning models. Code available at https://github.com/ky295/reasoning-manipulation

📄 PDF Abstract BibTeX arXiv:2507.03167

Code (1)

ky295/reasoning-manipulation 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Adversarial Manipulation of Deep Representations

2015-11-16 · Sara Sabour, Yanshuai Cao, Fartash Faghri, David J. Fleet

We show that the representation of an image in a deep neural network (DNN) can be manipulated to mimic those of other natural images, with only minor, imperceptible perturbations to the original image. Previous methods f…

Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models

2025-02-03 · Yuyang Gong, Zhuo Chen, Miaokun Chen, Fengchang Yu 외

Retrieval-Augmented Generation (RAG) systems based on Large Language Models (LLMs) have become essential for tasks such as question answering and content generation. However, their increasing impact on public opinion and…

Question AnsweringRAGRetrievalRetrieval-augmented Generation

Spatiotemporal Hidden-State Dynamics as a Signature of Internal Reasoning in Large Language Models

2026-05-03 · Kotaro Furuya, Takahito Tanimura arxiv

Large reasoning models (LRMs) generate extended solutions, yet it remains unclear whether these traces reflect substantive internal computation or merely verbosity and overthinking. Although recent hidden-state analyses …

Altered Thoughts, Altered Actions: Probing Chain-of-Thought Vulnerabilities in VLA Robotic Manipulation

2026-03-13 · Tuan Duong Trinh, Naveed Akhtar, Basim Azam arxiv

Recent Vision-Language-Action (VLA) models increasingly adopt chain-of-thought (CoT) reasoning, generating a natural-language plan before decoding motor commands. This internal text channel between the reasoning module a…

Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMs

2026-07-06 · Nikolaos Xiros, Maria-Eleni Zoumpoulidi, Georgios Paraskevopoulos arxiv

Although LLMs have made significant progress in mathematical reasoning, determining whether a mathematical problem is solvable remains a fundamental yet challenging capability. While recent studies have probed internal r…

Mathematical Reasoning