CVE-2026-53923

CVE-2026-53923 affects vLLM GGUF dequantize kernels. Root cause: integer truncation due to using int for the element count parameter, causing m*n (potentially > INT_MAX) to be truncated when passing to CUDA kernels, leading to unfilled output tensor memory that may retain data from previous in...

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

Large Language Models LLMs are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources. Existing defenses mainly focus on blocking malicious content at...

CVE-2026-44223

vLLM is an inference and serving engine for large language models LLMs. From to before 0.20.0, the extracthiddenstates speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash ...

Only 10% of SOCs Say They’re Getting Excellent Value From AI. Here’s What the Second Wave Has to Deliver

Eighteen months ago, the AI SOC was a marketing line. Today it's a budget item. The category has crossed over from interesting to inevitable, with billions of dollars now flowing into AI-powered security operations platforms, agentic SOC tools, and AI co-pilots built into every layer of the...

Steering LLM Viewpoints through Fabricated Evidence Injection

As chatbots increasingly influence daily decision-making, their potential to produce misleading responses poses substantial risks to users. This paper investigates a critical cognitive vulnerability in LLMs: their tendency to uncritically trust external context when presented with fabricated...

SHIELDS: Automating OS Hardening with Iterative Multi-Agent Remediation

Security misconfigurations remain a leading cause of OS-level compromise, and manually keeping systems compliant with standards like Defense Information Systems Agency DISA Security Technical Implementation Guides STIGs is a tedious and expensive process. Existing compliance automation tools can...

Backdoor Unlearning Generalization: A Path toward the Removal of Unknown Triggers in LLMs

Backdoor attacks in Large Language Models LLMs are a growing security concern, where models can generate adversary-chosen content. Existing defenses target backdoors one at a time and typically require knowledge of the trigger, leaving the defender at a structural disadvantage when unknown...

Cross-Vendor Sola ISPM Benchmark: Evaluating Agentic AI for Federated Identity Security Reasoning

The rapid proliferation of multi-cloud and SaaS platforms has transformed Identity Security Posture Management ISPM into a fundamentally cross-vendor challenge: critical misconfigurations and privilege escalation paths increasingly span multiple identity providers, infrastructure layers, and...

New Russia-Linked GREYVIBE Targets Ukraine with AI-Powered Cyberattacks

A previously undocumented threat actor dubbed GREYVIBE has been attributed to ongoing and persistent attacks targeting Ukraine and Ukraine-related entities since at least August 2025. GREYVIBE, per WithSecure, is assessed to be a Russian-speaking group operating broadly in the Russian time zone,...

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models

As Large Language Models evolve for user convenience, vulnerability to jailbreak attacks continues to be reported despite ongoing efforts in safety training. Traditional jailbreak techniques typically focus on a single prompt injection, neglecting the models' ability to remember the flow of...

Relevance As a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms that govern model outputs. Prior work shows that enabling...

S3C2 Summit 2025-07: Government Secure Supply Chain Summit

Software supply chains, while providing immense economic and software development value, are only as strong as their weakest link. Over the past several years, there has been an exponential increase in cyberattacks specifically targeting vulnerable links in critical software supply chains. The...

SAMD: A Tool for Identifying False Data Injection Scenarios in AI/ML-Enabled Medical Devices

The growing integration of artificial intelligence AI and machine learning ML in medical systems requires effective measures to address emerging security risks. One such risk is that of adversaries introducing false data through vulnerable system components during inference, causing misdiagnosis...

BAIT: Boundary-Guided Disclosure Escalation Via Self-Conditioned Reasoning

In this work, we propose BAIT Boundary-Aware Iterative Trap, a three-step jailbreak framework that approaches malicious goals through internal disclosure. BAIT first asks the model to identify the protection boundary, then requires it to refine that boundary, and finally requests a detailed...

MaxKB 代码问题漏洞

MaxKB is an open-source question-answering system based on large language models and RAG, developed by 1Panel-dev. Versions of MaxKB prior to 2.8.1 contained code vulnerabilities. These vulnerabilities stemmed from a server-side request forgeing vulnerability in the OSS file service URL retrieval...

Intelligent Detection and Mitigation of Carpet-Bombing DDoS Attacks in SDN Using Retrieval-Augmented Generation and Large Language Models

Software-Defined Networking SDN provides flexible and programmable network management; however, its centralized control architecture remains highly vulnerable to Distributed Denial-of-Service DDoS attacks, particularly Carpet-Bombing DDoS attacks that distribute malicious traffic across multiple...

APT-Agent: Automated Penetration Testing Using Large Language Models

Penetration testing is essential to securing modern web infrastructures, yet traditional manual methods struggle to keep pace with their scale and complexity. Large Language Models LLMs offer new opportunities for automating these tasks, but existing approaches face two persistent challenges:...

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...

AI Security Research Should Better Incentivize Defense Research

This work examines an imbalance in artificial intelligence AI security research: the field tends to produce more work on attacking AI systems than on defending them. Drawing on related academic papers, we find biased attack-to-defense ratios across subfields, including federated learning, speech...

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...