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...

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...

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...

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...

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...

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...

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...

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 ...

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...

A one-prompt attack that breaks LLM safety alignment

Large language models LLMs and diffusion models now power a wide range of applications, from document assistance to text-to-image generation, and users increasingly expect these systems to be safety-aligned by default. Yet safety alignment is only as robust as its weakest failure mode. Despite...

AI chat app leak exposes 300 million messages tied to 25 million users

An independent security researcher uncovered a major data breach affecting Chat & Ask AI, one of the most popular AI chat apps on Google Play and Apple App Store, with more than 50 million users. The researcher claims to have accessed 300 million messages from over 25 million users due to an...

RECUR: Resource Exhaustion Attack Via Recursive-Entropy Guided Counterfactual Utilization and Reflection

Large Reasoning Models LRMs employ reasoning to address complex tasks. Such explicit reasoning requires extended context lengths, resulting in substantially higher resource consumption. Prior work has shown that adversarially crafted inputs can trigger redundant reasoning processes, exposing LRMs...

ShallowJail: Steering Jailbreaks against Large Language Models

Large Language ModelsLLMs have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into producing harmful outputs. Existing jailbreaks are either...

Clouding the Mirror: Stealthy Prompt Injection Attacks Targeting LLM-Based Phishing Detection

Phishing sites continue to grow in volume and sophistication. Recent work leverages large language models LLMs to analyze URLs, HTML, and rendered content to decide whether a website is a phishing site. While these approaches are promising, LLMs are inherently vulnerable to prompt injection PI...

Detecting backdoored language models at scale

Today, we are releasing new research on detecting backdoors in open-weight language models. Our research highlights several key properties of language model backdoors, laying the groundwork for a practical scanner designed to detect backdoored models at scale and improve overall trust in AI...

Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents

Large language models LLMs have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to limited interaction, weak execution grounding, and a lack of experience reuse. We propose Co-RedTeam, a security-aware...

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers

Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in causal language models. Our approach relies on two key findings: first, sleeper agents tend to memorize poisoning dat...

Toxic_Flow_Analysis_Framework_For_Agentic_AI

Toxic Flow Analysis TFA Framework A Secure-by-Design framew...

Iran-Linked RedKitten Cyber Campaign Targets Human Rights NGOs and Activists

A Farsi-speaking threat actor aligned with Iranian state interests is suspected to be behind a new campaign targeting non-governmental organizations and individuals involved in documenting recent human rights abuses. The activity, observed by HarfangLab in January 2026, has been codenamed...