HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense

Jailbreak attacks pose significant threats to large language models LLMs, enabling attackers to bypass safeguards. However, existing reactive defense approaches struggle to keep up with the rapidly evolving multi-turn jailbreaks, where attackers continuously deepen their attacks to exploit...

RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models

As large language models LLMs become integral to safety-critical applications, ensuring their robustness against adversarial prompts is paramount. However, existing red teaming datasets suffer from inconsistent risk categorizations, limited domain coverage, and outdated evaluations, hindering...

A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-Case Prototypes

Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these systems enable continuous, autonomous workflows in real-world...

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...

TFSMLayer bypasses `safe_mode=True`, allowing attacker-controlled code execution during model inference

Summary TFSMLayer allows loading attacker-controlled TensorFlow SavedModels when deserializing a .keras model, even when safemode=True the default. While TensorFlow does not execute SavedModel functions during load, the attacker-controlled graph is registered during deserialization and executes...

CVE-2025-52516

An issue was discovered in the Camera in Samsung Mobile Processor and Wearable Processor Exynos 1330, 1380, 1480, 2400, 1580, 2500. An invalid kernel address dereference in the issimian device driver leads to a denial of service...

SAMSUNG多款产品 安全漏洞

SAMSUNG Wearable Processor and others are products of the South Korean company Samsung.SAMSUNG Wearable Processor is a series of wearable processors.SAMSUNG Exynos 990 is a mobile processor.SAMSUNG Exynos 850 is a mobile processor. SAMSUNG Exynos 850 is a mobile processor. A security vulnerabilit...

Quantum AI for Cybersecurity: A Hybrid Quantum-Classical Models for Attack Path Analysis

Modern cyberattacks are increasingly complex, posing significant challenges to classical machine learning methods, particularly when labeled data is limited and feature interactions are highly non-linear. In this study we investigates the potential of hybrid quantum-classical learning to enhance...

OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs

The rapid integration of Multimodal Large Language Models MLLMs into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to single-turn text interactions, and lack the scalability required for...

AI-Powered Hybrid Intrusion Detection Framework for Cloud Security Using Novel Metaheuristic Optimization

Cybersecurity poses considerable problems to Cloud Computing CC, especially regarding Intrusion Detection Systems IDSs, facing difficulties with skewed datasets and suboptimal classification model performance. This study presents the Hybrid Intrusion Detection System HyIDS, an innovative IDS that...

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...

Cracking IoT Security: Can LLMs Outsmart Static Analysis Tools?

Smart home IoT platforms such as openHAB rely on Trigger Action Condition TAC rules to automate device behavior, but the interplay among these rules can give rise to interaction threats, unintended or unsafe behaviors emerging from implicit dependencies, conflicting triggers, or overlapping...

CVE-2025-15391 D-Link DIR-806A SSDP Request ssdpcgi_main command injection

A weakness has been identified in D-Link DIR-806A 100CNb11. Affected is the function ssdpcgimain of the component SSDP Request Handler. This manipulation causes command injection. The attack can be initiated remotely. The exploit has been made available to the public and could be exploited. This...

GHSA-46H3-79WF-XR6C Picklescan is vulnerable to RCE via missing detection when calling built-in python _operator.attrgetter

Summary Picklescan uses operator.attrgetter, which is a built-in python library function to execute remote pickle files. Details The attack payload executes in the following steps: - First, the attacker crafts the payload by calling the operator.attrgetter function in the reduce method. - Then,...

GHSA-X843-G5MX-G377 Picklescan is vulnerable to RCE through missing detection when calling built-in python operator.methodcaller

Summary Picklescan uses operator.methodcaller, which is a built-in python library function to execute remote pickle files. Details The attack payload executes in the following steps: - First, the attacker crafts the payload by calling the operator.methodcaller function in method reduce. - Then,...

GHSA-VQMV-47XG-9WPR Picklescan missing detection when calling pty.spawn

Summary Using pty.spawn, which is a built-in python library function to execute arbitrary commands on the host system. Details The attack payload executes in the following steps: First, the attacker craft the payload by calling to pty.spawn function in the reduce method. Then the victim attempts ...

Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation

The software supply chain attacks are becoming more and more focused on trusted development and delivery procedures, so the conventional post-build integrity mechanisms cannot be used anymore. The available frameworks like SLSA, SBOM and in toto are majorly used to offer provenance and traceabili...

Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack

Audio-language models combine audio encoders with large language models to enable multimodal reasoning, but they also introduce new security vulnerabilities. We propose a universal targeted latent space attack, an encoder-level adversarial attack that manipulates audio latent representations to...

Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems

Machine learning ML underpins foundation models in finance, healthcare, and critical infrastructure, making them targets for data poisoning, model extraction, prompt injection, automated jailbreaking, and preference-guided black-box attacks that exploit model comparisons. Larger models can be mor...

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...