When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-Offs

Jailbreak defenses are essential for protecting large language models LLMs, but they can also introduce secondary costs that weaken model utility. We present a systematic study of these defense trade-offs along three dimensions: performance impact, over-refusal on benign inputs, and inference cos...

MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems

Multi-agent systems MAS are increasingly used to automate complex, distributed workflows. However, their inter-agent communication channels introduce new attack surfaces that remain poorly understood and are difficult to defend against. In this paper, we address how defenders should prioritize...

RAVEN: Agentic RAG for Automated Vulnerability Repair

Automated vulnerability repair has emerged as a promising direction to mitigate the growing number of software vulnerabilities. Recent advances in Large Language Models LLMs have further accelerated research in automated repair. However, existing frameworks remain largely restricted to...

SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents

Large language model LLM reviewers are increasingly used in pull-request PR workflows, where their approvals help decide which code is merged into a repository. This raises a question that benchmarks for static vulnerability detection or code generation do not address: can an automated reviewer...

Can Open-Source LLM Agents Replace Static Application Security Testing Tools? an Empirical Assessment

This paper explores the value of agentic AI tools for cybersecurity purposes. We evaluate the efficacy of a general-purpose GenAI Large Language Model- GenAI- based agent when powered by three different Ollama-hosted general-purpose open source models. We assess each agent's performance using...

Assessing Automated Prompt Injection Attacks in Agentic Environments

Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain underexplored in realistic agentic settings. We present a comprehensive empirical evaluation of automated prompt...

Security Is Relative: Training-Free Vulnerability Detection Via Multi-Agent Behavioral Contract Synthesis

Deep learning for vulnerability detection has shown promising results on early benchmarks, but recent evaluations reveal catastrophic degradation: models achieving F1 0.68 on legacy datasets collapse to 0.031 under strict deduplication. We identify the root cause as the semantic ambiguity problem...

When Safe Models Merge into Danger: Exploiting Latent Vulnerabilities in LLM Fusion

Model merging has emerged as a powerful technique for combining specialized capabilities from multiple fine-tuned LLMs without additional training costs. However, the security implications of this widely-adopted practice remain critically underexplored. In this work, we reveal that model merging...

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...

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,...

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models

Jailbreaking large language models LLMs has emerged as a critical security challenge with the widespread deployment of conversational AI systems. Adversarial users exploit these models through carefully crafted prompts to elicit restricted or unsafe outputs, a phenomenon commonly referred to as...

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...

Blue Teaming Function-Calling Agents

We present an experimental evaluation that assesses the robustness of four open source LLMs claiming function-calling capabilities against three different attacks, and we measure the effectiveness of eight different defences. Our results show how these models are not safe by default, and how the...

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...

How Can We Effectively Use LLMs for Phishing Detection?: Evaluating the Effectiveness of Large Language Model-Based Phishing Detection Models

Large language models LLMs have emerged as a promising phishing detection mechanism, addressing the limitations of traditional deep learning-based detectors, including poor generalization to previously unseen websites and a lack of interpretability. However, LLMs' effectiveness for phishing...

AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence

Large Language Models LLMs have demonstrated strong capabilities in natural language reasoning, yet their application to Cyber Threat Intelligence CTI remains limited. CTI analysis involves distilling large volumes of unstructured reports into actionable knowledge, a process where LLMs could...

On Selecting Few-Shot Examples for LLM-Based Code Vulnerability Detection

Large language models LLMs have demonstrated impressive capabilities for many coding tasks, including summarization, translation, completion, and code generation. However, detecting code vulnerabilities remains a challenging task for LLMs. An effective way to improve LLM performance is in-context...

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...

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...

When Intelligence Fails: An Empirical Study on Why LLMs Struggle with Password Cracking

The remarkable capabilities of Large Language Models LLMs in natural language understanding and generation have sparked interest in their potential for cybersecurity applications, including password guessing. In this study, we conduct an empirical investigation into the efficacy of pre-trained LL...