Bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs

With the rapid advancement of large language models LLMs, their robustness against adversarial manipulations, particularly jailbreak backdoor attacks, has become critically important. Existing approaches to embedding jailbreak triggers--such as supervised fine-tuning SFT, model editing, and...

LLM-Based Vulnerability Discovery through the Lens of Code Metrics

Large language models LLMs excel in many tasks of software engineering, yet progress in leveraging them for vulnerability discovery has stalled in recent years. To understand this phenomenon, we investigate LLMs through the lens of classic code metrics. Surprisingly, we find that a classifier...

VulnCheck KEV: CVE-2025-45985

Blink routers BL-WR9000 V2.4.9 , BL-AC2100AZ3 V1.0.4, BL-X10AC8 v1.0.5 , BL-LTE300 v1.2.3, BL-F1200AT1 v1.0.0, BL-X26AC8 v1.2.8, BLAC450MAE4 v4.0.0 and BL-X26DA3 v1.2.7 were discovered to contain a command injection vulnerability via the bsSetSSIDHide function...

LB-Link多款产品 安全漏洞

LB-Link BL-AC2100AZ3 and others are a wireless router from China Bilink LB-Link. A security vulnerability exists in various LB-Link products, which originates from an unauthorized command injection in the /goform/setserialcfg interface, which may result in the remote execution of malicious...

CVE-2025-57685

The LB-Link routers, including the BL-AC2100AZ3 V1.0.4, BL-WR4000 v2.5.0, BL-WR9000AE4 v2.4.9, BL-AC1900AZ2 v1.0.2, BL-X26AC8 v1.2.8, and BL-LTE300DA4 V1.2.3 models, are vulnerable to unauthorized command injection. Attackers can exploit this vulnerability by accessing the /goform/setserialcfg...

SilentStriker: toward Stealthy Bit-Flip Attacks on Large Language Models

The rapid adoption of large language models LLMs in critical domains has spurred extensive research into their security issues. While input manipulation attacks e.g., prompt injection have been well studied, Bit-Flip Attacks BFAs -- which exploit hardware vulnerabilities to corrupt model paramete...

PT-2025-39007

The LB-Link routers, including the BL-AC2100 AZ3 V1.0.4, BL-WR4000 v2.5.0, BL-WR9000 AE4 v2.4.9, BL-AC1900 AZ2 v1.0.2, BL-X26 AC8 v1.2.8, and BL-LTE300 DA4 V1.2.3 models, are vulnerable to unauthorized command injection. Attackers can exploit this vulnerability by accessing the /goform/set serial...

A Comparative Analysis of Ensemble-Based Machine Learning Approaches with Explainable AI for Multi-Class Intrusion Detection in Drone Networks

The growing integration of drones into civilian, commercial, and defense sectors introduces significant cybersecurity concerns, particularly with the increased risk of network-based intrusions targeting drone communication protocols. Detecting and classifying these intrusions is inherently...

Flowise 代码注入漏洞

Flowise is a FlowiseAI open source tool for easily building LLM applications. A cross-site scripting vulnerability exists in Flowise version 3.0.5, which originates from a CustomMCP node directly executing user-entered JavaScript code and can be exploited by an attacker to cause remote code...

Coherence-Driven Inference for Cybersecurity

Large language models LLMs can compile weighted graphs on natural language data to enable automatic coherence-driven inference CDI relevant to red and blue team operations in cybersecurity. This represents an early application of automatic CDI that holds near- to medium-term promise for...

FakeSound2: a Benchmark for Explainable and Generalizable Deepfake Sound Detection

The rapid development of generative audio raises ethical and security concerns stemming from forged data, making deepfake sound detection an important safeguard against the malicious use of such technologies. Although prior studies have explored this task, existing methods largely focus on binary...

DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software Systems

Intelligent software systems powered by Large Language Models LLMs are increasingly deployed in critical sectors, raising concerns about their safety during runtime. Through an industry-academic collaboration when deploying an LLM-powered virtual customer assistant, a critical software engineerin...

"Digital Camouflage": the LLVM Challenge in LLM-Based Malware Detection

Large Language Models LLMs have emerged as promising tools for malware detection by analyzing code semantics, identifying vulnerabilities, and adapting to evolving threats. However, their reliability under adversarial compiler-level obfuscation is yet to be discovered. In this study, we empirical...

Time-of-Check Time-of-Use Attacks Against LLMs

This is a nice piece of research: "Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents".: Abstract: Large Language Model LLM-enabled agents are rapidly emerging across a wide range of applications, but their deployment introduces vulnerabilities with security...

Synergizing Static Analysis with Large Language Models for Vulnerability Discovery and Beyond

This report examines the synergy between Large Language Models LLMs and Static Application Security Testing SAST to improve vulnerability discovery. Traditional SAST tools, while effective for proactive security, are limited by high false-positive rates and a lack of contextual understanding...

SecureFixAgent: a Hybrid LLM Agent for Automated Python Static Vulnerability Repair

Modern software development pipelines face growing challenges in securing large codebases with extensive dependencies. Static analysis tools like Bandit are effective at vulnerability detection but suffer from high false positives and lack repair capabilities. Large Language Models LLMs, in...

Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism Via Probabilistically Ablating Refusal Direction

Jailbreak attacks pose persistent threats to large language models LLMs. Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and unrobust internal defense mechanisms. These limitations make...

Evil Vizier: Vulnerabilities of LLM-Integrated XR Systems

Extended reality XR applications increasingly integrate Large Language Models LLMs to enhance user experience, scene understanding, and even generate executable XR content, and are often called "AI glasses". Despite these potential benefits, the integrated XR-LLM pipeline makes XR applications...

LLM Jailbreak Detection for (Almost) Free!

Large language models LLMs enhance security through alignment when widely used, but remain susceptible to jailbreak attacks capable of producing inappropriate content. Jailbreak detection methods show promise in mitigating jailbreak attacks through the assistance of other models or multiple model...

ATLANTIS: AI-Driven Threat Localization, Analysis, and Triage Intelligence System

We present ATLANTIS, the cyber reasoning system developed by Team Atlanta that won 1st place in the Final Competition of DARPA's AI Cyber Challenge AIxCC at DEF CON 33 August 2025. AIxCC 2023-2025 challenged teams to build autonomous cyber reasoning systems capable of discovering and patching...