Recursive Language Models for Jailbreak Detection: A Procedural Defense for Tool-Augmented Agents

Jailbreak prompts are a practical and evolving threat to large language models LLMs, particularly in agentic systems that execute tools over untrusted content. Many attacks exploit long-context hiding, semantic camouflage, and lightweight obfuscations that can evade single-pass guardrails. We...

Mind the Gap: Evaluating LLMs for High-Level Malicious Package Detection Vs. Fine-Grained Indicator Identification

The prevalence of malicious packages in open-source repositories, such as PyPI, poses a critical threat to the software supply chain. While Large Language Models LLMs have emerged as a promising tool for automated security tasks, their effectiveness in detecting malicious packages and indicators...

Discovering Universal Activation Directions for PII Leakage in Language Models

Modern language models exhibit rich internal structure, yet little is known about how privacy-sensitive behaviors, such as personally identifiable information PII leakage, are represented and modulated within their hidden states. We present UniLeak, a mechanistic-interpretability framework that...

GrandStream GXP1600 Unauthenticated Remote Code Execution

An unauthenticated stack-based buffer overflow vulnerability exists in the HTTP API endpoint /cgi-bin/api.values.get. A remote attacker can leverage this vulnerability to achieve unauthenticated remote code execution RCE with root privileges on a target device. The vulnerability affects all six...

Grandstream GXP series 安全漏洞

The Grandstream GXP series is a series of IP phones produced by the American company Grandstream. There are security vulnerabilities in the Grandstream GXP series. These vulnerabilities stem from an unauthenticated, stack-based buffer overflow vulnerability in the /cgi-bin/api.values.get HTTP API...

Side-Channel Attacks Against LLMs

Here are three papers describing different side-channel attacks against LLMs. "Remote Timing Attacks on Efficient Language Model Inference": Abstract: Scaling up language models has significantly increased their capabilities. But larger models are slower models, and so there is now an extensive...

DARTH-PUM: A Hybrid Processing-Using-Memory Architecture

Analog processing-using-memory PUM; a.k.a. in-memory computing makes use of electrical interactions inside memory arrays to perform bulk matrix-vector multiplication MVM operations. However, many popular matrix-based kernels need to execute non-MVM operations, which analog PUM cannot directly...

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks

As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight models must primarily depend on internal safeguards to mitigate harmful behavior. Prior red-teaming research has largel...

AI Arms and Influence: Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises

Today's leading AI models engage in sophisticated behaviour when placed in strategic competition. They spontaneously attempt deception, signaling intentions they do not intend to follow; they demonstrate rich theory of mind, reasoning about adversary beliefs and anticipating their actions; and th...

What Hackers Talk about When They Talk about AI: Early-Stage Diffusion of a Cybercrime Innovation

The rapid expansion of artificial intelligence AI is raising concerns about its potential to transform cybercrime. Beyond empowering novice offenders, AI stands to intensify the scale and sophistication of attacks by seasoned cybercriminals. This paper examines the evolving relationship between...

Google Ties Suspected Russian Actor to CANFAIL Malware Attacks on Ukrainian Orgs

A previously undocumented threat actor has been attributed to attacks targeting Ukrainian organizations with malware known as CANFAIL. Google Threat Intelligence Group GTIG described the hacking group as possibly affiliated with Russian intelligence services. The threat actor is assessed to have...

In-Context Autonomous Network Incident Response: An End-To-End Large Language Model Agent Approach

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies through extensive simulation of the incident. While this...

Automatic Simplification of Common Vulnerabilities and Exposures Descriptions

Understanding cyber security is increasingly important for individuals and organizations. However, a lot of information related to cyber security can be difficult to understand to those not familiar with the topic. In this study, we focus on investigating how large language models LLMs could be...

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...

An Empirical Study of the Imbalance Issue in Software Vulnerability Detection

Vulnerability detection is crucial to protect software security. Nowadays, deep learning DL is the most promising technique to automate this detection task, leveraging its superior ability to extract patterns and representations within extensive code volumes. Despite its promise, DL-based...

AMD Processors 安全漏洞

AMD Processors are a series of processors developed by American semiconductor company AMD. There is a security vulnerability in AMD Processors, which stems from type confusion. This vulnerability may allow attackers to send malformed parameters to external global memory interconnection trusted...

GoodVibe: Security-By-Vibe for LLM-Based Code Generation

Large language models LLMs are increasingly used for code generation in fast, informal development workflows, often referred to as vibe coding, where speed and convenience are prioritized, and security requirements are rarely made explicit. In this setting, models frequently produce functionally...

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...

TRACE: Timely Retrieval and Alignment for Cybersecurity Knowledge Graph Construction and Expansion

The rapid evolution of cyber threats has highlighted significant gaps in security knowledge integration. Cybersecurity Knowledge Graphs CKGs relying on structured data inherently exhibit hysteresis, as the timely incorporation of rapidly evolving unstructured data remains limited, potentially...

Vulnerabilities in Partial TEE-Shielded LLM Inference with Precomputed Noise

The deployment of large language models LLMs on third-party devices requires new ways to protect model intellectual property. While Trusted Execution Environments TEEs offer a promising solution, their performance limits can lead to a critical compromise: using a precomputed, static secret basis ...