Case Study: Fine-Tuning Small Language Models for Accurate and Private CWE Detection in Python Code

Large Language Models LLMs have demonstrated significant capabilities in understanding and analyzing code for security vulnerabilities, such as Common Weakness Enumerations CWEs. However, their reliance on cloud infrastructure and substantial computational requirements pose challenges for analyzi...

CVE-2025-28025

TOTOLINK A830R V4.1.2cu.5182B20201102, A950RG V4.1.2cu.5161B20200903, A3000RU V5.9c.5185B20201128, and A3100R V4.1.2cu.5247B20211129 were found to contain a buffer overflow vulnerability in downloadFile.cgi through the v14 parameter...

Automatically Generating Rules of Malicious Software Packages Via Large Language Model

Today's security tools predominantly rely on predefined rules crafted by experts, making them poorly adapted to the emergence of software supply chain attacks. To tackle this limitation, we propose a novel tool, RuleLLM, which leverages large language models LLMs to automate rule generation for O...

AiXamine: Simplified LLM Safety and Security

Evaluating Large Language Models LLMs for safety and security remains a complex task, often requiring users to navigate a fragmented landscape of ad hoc benchmarks, datasets, metrics, and reporting formats. To address this challenge, we present aiXamine, a comprehensive black-box evaluation...

Private Federated Learning Using Preference-Optimized Synthetic Data

In practical settings, differentially private Federated learning DP-FL is the dominant method for training models from private, on-device client data. Recent work has suggested that DP-FL may be enhanced or outperformed by methods that use DP synthetic data Wu et al., 2024; Hou et al., 2024. The...

Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-Based Multi-Agent Debate

Multi-Agent Debate MAD, leveraging collaborative interactions among Large Language Models LLMs, aim to enhance reasoning capabilities in complex tasks. However, the security implications of their iterative dialogues and role-playing characteristics, particularly susceptibility to jailbreak attack...

CVE-2025-28026

TOTOLINK A830R V4.1.2cu.5182B20201102, A950RG V4.1.2cu.5161B20200903, A3000RU V5.9c.5185B20201128, and A3100R V4.1.2cu.5247B20211129 were found to contain a buffer overflow vulnerability in downloadFile.cgi...

GO-2025-3622 Mattermost doesn't restrict domains LLM can request to contact upstream in github.com/mattermost/mattermost-server

Mattermost doesn't restrict domains LLM can request to contact upstream in github.com/mattermost/mattermost-server...

CVE-2025-28033

TOTOLINK A800R V4.1.2cu.5137B20200730, A810R V4.1.2cu.5182B20201026, A830R V4.1.2cu.5182B20201102, A950RG V4.1.2cu.5161B20200903, A3000RU V5.9c.5185B20201128, and A3100R V4.1.2cu.5247B20211129 were found to contain a pre-auth buffer overflow vulnerability in the setNoticeCfg function through the...

DoomArena: a Framework for Testing AI Agents against Evolving Security Threats

We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1 It is a plug-in framework and integrates easily into realistic agentic frameworks like BrowserGym for web agents and $τ$-bench for tool calling agents; 2 It is configurable and allows...

ReGraph: a Tool for Binary Similarity Identification

Binary Code Similarity Detection BCSD is not only essential for security tasks such as vulnerability identification but also for code copying detection, yet it remains challenging due to binary stripping and diverse compilation environments. Existing methods tend to adopt increasingly complex...

TOTOLINK多款产品 安全漏洞

TOTOLINK A800R and others are products of China Gion Electronics TOTOLINK.TOTOLINK A800R is a wireless router.TOTOLINK A830R is a wireless dual-band router.TOTOLINK A810R is a wireless dual-band router.TOTOLINK A810R is a wireless dual-band router.TOTOLINK A810R is a wireless dual-band...

CVE-2025-28027

TOTOLINK A830R V4.1.2cu.5182B20201102, A950RG V4.1.2cu.5161B20200903, A3000RU V5.9c.5185B20201128, and A3100R V4.1.2cu.5247B20211129 was found to contain a buffer overflow vulnerability in downloadFile.cgi...

A Time Series Analysis of Malware Uploads to Programming Language Ecosystems

Software ecosystems built around programming languages have greatly facilitated software development. At the same time, their security has increasingly been acknowledged as a problem. To this end, the paper examines the previously overlooked longitudinal aspects of software ecosystem security,...

TOTOLINK多款产品 安全漏洞

TOTOLINK A800R and others are products of China Gion Electronics TOTOLINK.TOTOLINK A800R is a wireless router.TOTOLINK A830R is a wireless dual-band router.TOTOLINK A810R is a wireless dual-band router.TOTOLINK A810R is a wireless dual-band router.TOTOLINK A810R is a wireless dual-band...

CVE-2025-28032

TOTOLINK A800R V4.1.2cu.5137B20200730, A810R V4.1.2cu.5182B20201026, A830R V4.1.2cu.5182B20201102, A950RG V4.1.2cu.5161B20200903, A3000RU V5.9c.5185B20201128, and A3100R V4.1.2cu.5247B20211129 contain a pre-auth buffer overflow vulnerability in the setNoticeCfg function through the IpForm paramet...

FLARE: Feature-Based Lightweight Aggregation for Robust Evaluation of IoT Intrusion Detection

The proliferation of Internet of Things IoT devices has expanded the attack surface, necessitating efficient intrusion detection systems IDSs for network protection. This paper presents FLARE, a feature-based lightweight aggregation for robust evaluation of IoT intrusion detection to address the...

Zero Day Malware Detection with Alpha: Fast DBI with Transformer Models for Real World Application

The effectiveness of an AI model in accurately classifying novel malware hinges on the quality of the features it is trained on, which in turn depends on the effectiveness of the analysis tool used. Peekaboo, a Dynamic Binary Instrumentation DBI tool, defeats malware evasion techniques to capture...

Backdoor Defense in Diffusion Models Via Spatial Attention Unlearning

Text-to-image diffusion models are increasingly vulnerable to backdoor attacks, where malicious modifications to the training data cause the model to generate unintended outputs when specific triggers are present. While classification models have seen extensive development of defense mechanisms,...

DualBreach: Efficient Dual-Jailbreaking Via Target-Driven Initialization and Multi-Target Optimization

Recent research has focused on exploring the vulnerabilities of Large Language Models LLMs, aiming to elicit harmful and/or sensitive content from LLMs. However, due to the insufficient research on dual-jailbreaking -- attacks targeting both LLMs and Guardrails, the effectiveness of existing...