Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs

Large Language ModelsLLMs are widely deployed, yet are vulnerable to jailbreak prompts that elicit policy-violating outputs. Although prior studies have uncovered these risks, they typically treat all tokens as equally important during prompt mutation, overlooking the varying contributions of...

A Framework for Formalizing LLM Agent Security

Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective is being pursued, and whether the action serves that objective. However,...

Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models

Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law framework for jailbreaks by treating each attack as a...

Analysis of LLMs against Prompt Injection and Jailbreak Attacks

Large Language Models LLMs are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same time, LLMs are vulnerable to prompt-based attacks. Thus,...

Sparse Autoencoders Are Capable LLM Jailbreak Mitigators

Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering CC-Delta, an SAE-based defense that identifies jailbreak-relevant sparse features by comparing token-level representations of the same harmful request with and without...

ShallowJail: Steering Jailbreaks against Large Language Models

Large Language ModelsLLMs have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into producing harmful outputs. Existing jailbreaks are either...

Now You Hear Me: Audio Narrative Attacks against Large Audio-Language Models

Large audio-language models increasingly operate on raw speech inputs, enabling more seamless integration across domains such as voice assistants, education, and clinical triage. This transition, however, introduces a distinct class of vulnerabilities that remain largely uncharacterized. We exami...

RvB: Automating AI System Hardening Via Iterative Red-Blue Games

The dual offensive and defensive utility of Large Language Models LLMs highlights a critical gap in AI security: the lack of unified frameworks for dynamic, iterative adversarial adaptation hardening. To bridge this gap, we propose the Red Team vs. Blue Team RvB framework, formulated as a...

TrojanPraise: Jailbreak LLMs Via Benign Fine-Tuning

The demand of customized large language models LLMs has led to commercial LLMs offering black-box fine-tuning APIs, yet this convenience introduces a critical security loophole: attackers could jailbreak the LLMs by fine-tuning them with malicious data. Though this security issue has recently bee...

Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models

Large Language Models LLMs face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, the practical effectiveness of existing attacks is undermined by several critical limitations: they struggle to maintain ...

Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks Via Reinforcement Learning

Large language models LLMs have demonstrated remarkable capabilities across diverse applications, however, they remain critically vulnerable to jailbreak attacks that elicit harmful responses violating human values and safety guidelines. Despite extensive research on defense mechanisms, existing...

Jailbreaking LLMs and VLMs: Mechanisms, Evaluation, and Unified Defense

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models LLMs and Vision-Language Models VLMs, emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training data, linguistic ambiguity, and generative uncertainty. It...

Emoji-Based Jailbreaking of Large Language Models

Large Language Models LLMs are integral to modern AI applications, but their safety alignment mechanisms can be bypassed through adversarial prompt engineering. This study investigates emoji-based jailbreaking, where emoji sequences are embedded in textual prompts to trigger harmful and unethical...

EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models Via Equation Solving and Code Completion

Large language models LLMs, such as ChatGPT, have achieved remarkable success across a wide range of fields. However, their trustworthiness remains a significant concern, as they are still susceptible to jailbreak attacks aimed at eliciting inappropriate or harmful responses. However, existing...

CVE-2018-25143

CVE-2018-25143 affects Microhard Systems IPn4G 1.1.0. A service vulnerability enables authenticated users to turn on a restricted SSH shell via the default user 'msshc'. An attacker can abuse a custom 'ping' command within the NcFTP environment to escape the restricted shell and execute commands ...

Odysseus: Jailbreaking Commercial Multimodal LLM-Integrated Systems Via Dual Steganography

By integrating language understanding with perceptual modalities such as images, multimodal large language models MLLMs constitute a critical substrate for modern AI systems, particularly intelligent agents operating in open and interactive environments. However, their increasing accessibility al...

Efficient Jailbreak Mitigation Using Semantic Linear Classification in a Multi-Staged Pipeline

Prompt injection and jailbreaking attacks pose persistent security challenges to large language model LLM-based systems. We present an efficient and systematically evaluated defense architecture that mitigates these threats through a lightweight, multi-stage pipeline. Its core component is a...

Honeywell Multiple Industrial Printers Improper Privilege Management (CVE-2017-5671)

Honeywell Intermec PM23, PM42, PM43, PC23, PC43, PD43, and PC42 industrial printers before 10.11.013310 and 10.12.x before 10.12.013309 have /usr/bin/lua installed setuid to the itadmin account, which allows local users to conduct a BusyBox jailbreak attack and obtain root privileges by overwriti...

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

Finetuning pretrained large language models LLMs has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak vulnerabilities from their pretrained sources. We investigat...

RunawayEvil: Jailbreaking the Image-To-Video Generative Models

Image-to-Video I2V generation synthesizes dynamic visual content from image and text inputs, providing significant creative control. However, the security of such multimodal systems, particularly their vulnerability to jailbreak attacks, remains critically underexplored. To bridge this gap, we...