VulnLLM-R

VulnLLM-R: LLM de razonamiento especializado para la detección de vulnerabilidades Artículo: arXiv:2512.07533 Código y datos: GitHub Demo: Demo web Modelo: Modelo 7B Entorno y conjunto de datos 🛠️ Crear el entorno Instalar Git LFS y clonar el repositorio los archivos LFS se descargan...

deleting-the-trace

Ataques de inyección de tokens de control contra agentes que utilizan herramientas Código y mediciones registradas para un estudio de dos ataques a nivel de entrada contra agentes de modelos de lenguaje que utilizan herramientas. El primer ataque añade una cadena corta de los propios tokens de...

masq

Sit where the model sits. See what it can see. MASQ MASQ is a local security CLI for AI agent stacks. It sits in the same seat the model sits in: it reads MCP tool catalogs, completes the MCP handshake, looks through session logs, and probes local model HTTP ports. Then it prints findings and...

Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-Of-Thought in Frontier Models

The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-source systems are hidden. By registering a simple custom tool through a standard API feature, we induce frontier models to...

U.S. Agencies Accuse China AI Firms of Distilling Claude, GPT, Gemini, and Grok

U.S. cybersecurity and intelligence agencies have accused China-based artificial intelligence AI companies of conducting "systematic extraction" of proprietary functionalities and capabilities of American frontier models through distillation attacks. The activity has been described as occurring a...

The Implications of Linguistic Illegibility for LLM Security

LLMs are trained to generate natural language. However, various strands of evidence indicate that an LLM's externalized linguistic outputs and mechanistically-extracted linguistic features can be an unreliable lens for understanding internal model computation. We introduce the term "linguistic...

Stealing Reasoning Traces from Proprietary LLM APIs

Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the...

Evading Chain-Of-Thought Monitoring through Model Poisoning

Chain-of-thought CoT monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning trace is informative about its actions. This work studies the limits of CoT monitoring through the lens of model poisoning. We demonstrate that backdoor...

Cybersecurity Detection Classification with Reasoning-Enabled Language Models

A major issue in Security Operations Centers SOCs is alert fatigue, as the number of detections reported is more than staff can triage in a given day. Prior work prompts or fine-tunes large language models LLMs to emit a triage label directly, but does not train them to reason about whether a...

GDM AI Control Roadmap

AI agents are rapidly accelerating work at frontier AI companies, helping with AI R&D, cyber-defence, and advancing scientific discoveries. As these agents become more tightly integrated into our systems, unlocking their full potential requires rethinking how we do security. We should not assume...

Reasoning As an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs

Large Reasoning Models LRMs have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their explicit chain-of-thought CoT mechanism introduces new security risks, making them particularly vulnerable to jailbreak...

An Empirical Evaluation of LLM-Generated Code Security across Prompting Methods

The growing use of Large Language Models LLMs for automated code generation has enhanced software development efficiency, but often at the cost of security. Generated code frequently overlooks critical concerns, leaving it vulnerable to issues such as weak encryption and improper input validation...

Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks

System Instructions in Large Language Models LLMs are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive information such as API credentials, internal policies, and...

Bypassing AI Control Protocols Via Agent-As-A-Proxy Attacks

As AI agents automate critical workloads, they remain vulnerable to indirect prompt injection IPI attacks. Current defenses rely on monitoring protocols that jointly evaluate an agent's Chain-of-Thought CoT and tool-use actions to ensure alignment with user intent. We demonstrate that these...

Rethinking On-Device LLM Reasoning: Why Analogical Mapping Outperforms Abstract Thinking for IoT DDoS Detection

The rapid expansion of IoT deployments has intensified cybersecurity threats, notably Distributed Denial of Service DDoS attacks, characterized by increasingly sophisticated patterns. Leveraging Generative AI through On-Device Large Language Models ODLLMs provides a viable solution for real-time...

CoTDeceptor:Adversarial Code Obfuscation against CoT-Enhanced LLM Code Agents

LLM-based code agentse.g., ChatGPT Codex are increasingly deployed as detector for code review and security auditing tasks. Although CoT-enhanced LLM vulnerability detectors are believed to provide improved robustness against obfuscated malicious code, we find that their reasoning chains and...

ReVul-CoT: Towards Effective Software Vulnerability Assessment with Retrieval-Augmented Generation and Chain-Of-Thought Prompting

Context: Software Vulnerability Assessment SVA plays a vital role in evaluating and ranking vulnerabilities in software systems to ensure their security and reliability. Objective: Although Large Language Models LLMs have recently shown remarkable potential in SVA, they still face two major...

Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies

Large language models LLMs have become indispensable for automated code generation, yet the quality and security of their outputs remain a critical concern. Existing studies predominantly concentrate on adversarial attacks or inherent flaws within the models. However, a more prevalent yet...

XOffense: an AI-Driven Autonomous Penetration Testing Framework with Offensive Knowledge-Enhanced LLMs and Multi Agent Systems

This work introduces xOffense, an AI-driven, multi-agent penetration testing framework that shifts the process from labor-intensive, expert-driven manual efforts to fully automated, machine-executable workflows capable of scaling seamlessly with computational infrastructure. At its core, xOffense...

CryptoScope: Utilizing Large Language Models for Automated Cryptographic Logic Vulnerability Detection

Cryptographic algorithms are fundamental to modern security, yet their implementations frequently harbor subtle logic flaws that are hard to detect. We introduce CryptoScope, a novel framework for automated cryptographic vulnerability detection powered by Large Language Models LLMs. CryptoScope...