NegBLEURT Forest: Leveraging Inconsistencies for Detecting Jailbreak Attacks

Jailbreak attacks designed to bypass safety mechanisms pose a serious threat by prompting LLMs to generate harmful or inappropriate content, despite alignment with ethical guidelines. Crafting universal filtering rules remains difficult due to their inherent dependence on specific contexts. To...

StyleBreak: Revealing Alignment Vulnerabilities in Large Audio-Language Models Via Style-Aware Audio Jailbreak

Large Audio-language Models LAMs have recently enabled powerful speech-based interactions by coupling audio encoders with Large Language Models LLMs. However, the security of LAMs under adversarial attacks remains underexplored, especially through audio jailbreaks that craft malicious audio promp...

EASE: Practical and Efficient Safety Alignment for Small Language Models

Small language models SLMs are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust protection, particularly against adversarial jailbreaks. While...

KG-DF: A Black-Box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs

With the widespread application of large language models LLMs in various fields, the security challenges they face have become increasingly prominent, especially the issue of jailbreak. These attacks induce the model to generate erroneous or uncontrolled outputs through crafted inputs, threatenin...

Jailbreaking in the Haystack

Recent advances in long-context language models LMs have enabled million-token inputs, expanding their capabilities across complex tasks like computer-use agents. Yet, the safety implications of these extended contexts remain unclear. To bridge this gap, we introduce NINJA short for...

Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses

Multimodal large language models MLLMs comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to induce unauthorized or harmful responses. The incorporation o...

The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning

Large Language Models LLMs have advanced rapidly and now encode extensive world knowledge. Despite safety fine-tuning, however, they remain susceptible to adversarial prompts that elicit harmful content. Existing jailbreak techniques fall into two categories: white-box methods e.g., gradient-base...

Jailbreak Mimicry: Automated Discovery of Narrative-Based Jailbreaks for Large Language Models

Large language models LLMs remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry, a systematic methodology for training compact attacker mode...

HarmNet: A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models

Large Language Models LLMs remain vulnerable to multi-turn jailbreak attacks. We introduce HarmNet, a modular framework comprising ThoughtNet, a hierarchical semantic network; a feedback-driven Simulator for iterative query refinement; and a Network Traverser for real-time adaptive attack...

Multimodal Safety Is Asymmetric: Cross-Modal Exploits Unlock Black-Box MLLMs Jailbreaks

Multimodal large language models MLLMs have demonstrated significant utility across diverse real-world applications. But MLLMs remain vulnerable to jailbreaks, where adversarial inputs can collapse their safety constraints and trigger unethical responses. In this work, we investigate jailbreaks i...

BreakFun: Jailbreaking LLMs Via Schema Exploitation

The proficiency of Large Language Models LLMs in processing structured data and adhering to syntactic rules is a capability that drives their widespread adoption but also makes them paradoxically vulnerable. In this paper, we investigate this vulnerability through BreakFun, a jailbreak methodolog...

SoK: Taxonomy and Evaluation of Prompt Security in Large Language Models

Large Language Models LLMs have rapidly become integral to real-world applications, powering services across diverse sectors. However, their widespread deployment has exposed critical security risks, particularly through jailbreak prompts that can bypass model alignment and induce harmful outputs...

Active Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreaks

Large language models LLMs are increasingly vulnerable to multi-turn jailbreak attacks, where adversaries iteratively elicit harmful behaviors that bypass single-turn safety filters. Existing defenses predominantly rely on passive rejection, which either fails against adaptive attackers or overly...

ArtPerception: ASCII Art-Based Jailbreak on LLMs with Recognition Pre-Test

The integration of Large Language Models LLMs into computer applications has introduced transformative capabilities but also significant security challenges. Existing safety alignments, which primarily focus on semantic interpretation, leave LLMs vulnerable to attacks that use non-standard data...

EUVD-2017-14748

Malware in sbrugna...

EUVD-2019-13873

Malware in sbrugna...

EUVD-2018-5057

Malware in sbrugna...

EUVD-2020-24952

Malware in sbrugna...

EUVD-2025-14804

Malicious code in bioql PyPI...

External Data Extraction Attacks against Retrieval-Augmented Large Language Models

In recent years, RAG has emerged as a key paradigm for enhancing large language models LLMs. By integrating externally retrieved information, RAG alleviates issues like outdated knowledge and, crucially, insufficient domain expertise. While effective, RAG introduces new risks of external data...