CORTEXA
← Browse
arxivcs.CRcs.AI2026-07-22

Geometric Configurations of Perturbed Jailbreak Prompts

Lynn Delcon, Andres Algaba, Vincent Ginis

Perturbation techniques that turn unsuccessful jailbreak prompts into successful ones are continuously evolving, constituting a major security threat to LLM safety. In this paper, we investigate the internal representations of such string-level perturbed jailbreak inputs in the small weight models of the Qwen-2.5-1.5B/-3B/-7B-Instruct and Llama-3.2-1B/-3B/-3.1-8B-Instruct families. We select two representation spaces: the last-layer-last-token embedding space and the top-50 next-token probability space. The former space separates prompts based on their spelling and format, while the latter space is effectively one-dimensional but appears more complex to cluster. Within our refusal-dominated answer set we find no behavioral hyperplane in either space. Only the next token "Sure" in the 1.5B Qwen model, and both tokens "," and "ĊĊ" in the 1$ Llama model, display a significant association with a compliant-labeled answer.

View free PDFSource page

Related papers

arxivcs.CRcs.AI2026-07-01

Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces

Junlong Liu, Haobo Wang, Weiqi Luo, Xiaojun Jia

Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs). While prior work has primarily studied attacks and defenses at the prompt level, we show that this prompt-centric paradigm overlooks a structural vulnerability in stateful, function…

View free PDFSource page
arxivcs.AIcs.CR2026-07-01

HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment

Shei Pern Chua, Hao Wu, Qianli Ma, Fangzhao Wu

Understanding how aligned LLMs internally represent safety is critical for diagnosing alignment vulnerabilities, as it explains why jailbreaks succeed and informs the design of robust alignment strategies. Prior work shows that aligned LLMs encode harmfulness and refusal as separ…

View free PDFSource page
arxivcs.CRcs.AI2026-07-11

Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety

Chigozirim Ifebi, Brent Kong, Ayushi Mehrotra

Safety alignment in large language models remains brittle across languages: prompts reliably refused in English can elicit harmful compliance in non-English and low-resource settings. We introduce \textsc{Minionese}, a multilingual jailbreak benchmark spanning 18 languages, 4 res…

View free PDFSource page
arxivcs.CRcs.AI2026-07-08

Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs

Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang, Longwei Wang

Large language models (LLMs) exhibit remarkable capabilities but remain highly vulnerable to adversarial prompts and jailbreak attacks. Existing approaches primarily analyze these failures through input-output behaviors or attribution methods, offering limited insight into how ad…

View free PDFSource page
arxivcs.CRcs.AI2026-07-17

Evaluating Open-Weight LLMs for Generating Structured Threat Information for Autonomous Vehicle Vulnerabilities

Md Erfan, Ahmed Ryan, Md Kamal Hossain Chowdhury, Md Rayhanur Rahman

Connected and Autonomous Vehicles (CAVs) rely on interconnected software and hardware components, including sensors, Electronic Control Units, in-vehicle infotainment systems, and telematics units, where vulnerabilities can compromise assets, users, and vehicle operations. These…

View free PDFSource page
arxivcs.LGcs.AIcs.CR2026-07-02

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail

Mahmoud Abdelfattah, Hamid Nasiri, Peter Garraghan

Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts. Existing guardrails predominantly rely on fine-tuning to build classifiers, which often suffer from low generalization and high inference la…

View free PDFSource page