79 matches found
OpenClaw Integrates VirusTotal Scanning to Detect Malicious ClawHub Skills
OpenClaw formerly Moltbot and Clawdbot has announced that it's partnering with Google-owned VirusTotal to scan skills that are being uploaded to ClawHub, its skill marketplace, as part of broader efforts to bolster the security of the agentic ecosystem. "All skills published to ClawHub are now...
The Semantic Trap: Do Fine-Tuned LLMs Learn Vulnerability Root Cause or Just Functional Pattern?
LLMs demonstrate promising performance in software vulnerability detection after fine-tuning. However, it remains unclear whether these gains reflect a genuine understanding of vulnerability root causes or merely an exploitation of functional patterns. In this paper, we identify a critical failur...
TrojanPraise: Jailbreak LLMs Via Benign Fine-Tuning
The demand of customized large language models LLMs has led to commercial LLMs offering black-box fine-tuning APIs, yet this convenience introduces a critical security loophole: attackers could jailbreak the LLMs by fine-tuning them with malicious data. Though this security issue has recently bee...
A Novel Contrastive Loss for Zero-Day Network Intrusion Detection
Machine learning has achieved state-of-the-art results in network intrusion detection; however, its performance significantly degrades when confronted by a new attack class -- a zero-day attack. In simple terms, classical machine learning-based approaches are adept at identifying attack classes o...
SourceBroken: A Large-Scale Analysis on the (Un)Reliability of SourceRank in the PyPI Ecosystem
SourceRank is a scoring system made of 18 metrics that assess the popularity and quality of open-source packages. Despite being used in several recent studies, none has thoroughly analyzed its reliability against evasion attacks aimed at inflating the score of malicious packages, thereby...
Better Call Graphs: A New Dataset of Function Call Graphs for Malware Classification
Function call graphs FCGs have emerged as a powerful abstraction for malware detection, capturing the behavioral structure of applications beyond surface-level signatures. Their utility in traditional program analysis has been well established, enabling effective classification and analysis of...
EUVD-2025-203260
The vulnerability arises when a client fetches a tools’ JSON specification, known as a Manual, from a remote Manual Endpoint. While a provider may initially serve a benign manual e.g., one defining an HTTP tool call, earning the clients’ trust, a malicious provider can later change the manual to...
Clustering Malware at Scale: A First Full-Benchmark Study
Recent years have shown that malware attacks still happen with high frequency. Malware experts seek to categorize and classify incoming samples to confirm their trustworthiness or prove their maliciousness. One of the ways in which groups of malware samples can be identified is through malware...
Towards Classifying Benign and Malicious Packages Using Machine Learning
Recently, the number of malicious open-source packages in package repositories has been increasing dramatically. While major security scanners focus on identifying known Common Vulnerabilities and Exposures CVEs in open-source packages, there are very few studies on detecting malicious packages...
BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-Tuning
Knowledge Distillation KD is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party repositories introduces serious security risks -- most notably backdoor attacks. Existing KD backdoor methods are typically complex and computationally...
How Can We Effectively Use LLMs for Phishing Detection?: Evaluating the Effectiveness of Large Language Model-Based Phishing Detection Models
Large language models LLMs have emerged as a promising phishing detection mechanism, addressing the limitations of traditional deep learning-based detectors, including poor generalization to previously unseen websites and a lack of interpretability. However, LLMs' effectiveness for phishing...
Malicious code in benign-lib (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 09477b048d84611002417894ccb3265d246be0156b096a8b47776960d45e9d3d Package hides an executable inside, and starts it when imported. The sandbox analysis shows only starting a calculator, which suggests it's a research attempt...
MAL-2025-191620 Malicious code in benign-lib (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 09477b048d84611002417894ccb3265d246be0156b096a8b47776960d45e9d3d Package hides an executable inside, and starts it when imported. The sandbox analysis shows only starting a calculator, which suggests it's a research attempt...
WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection attacks, but none have been systematically evaluated for web agents. In this work, we bridge this gap by presenting the first...
Contrastive Self-Supervised Network Intrusion Detection Using Augmented Negative Pairs
Network intrusion detection remains a critical challenge in cybersecurity. While supervised machine learning models achieve state-of-the-art performance, their reliance on large labelled datasets makes them impractical for many real-world applications. Anomaly detection methods, which train...
Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models
Large Language Models LLMs are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety mechanisms. Unlike overt attacks, these subtle prompts exploit...
Extending the OWASP Multi-Agentic System Threat Modeling Guide: Insights from Multi-Agent Security Research
We propose an extension to the OWASP Multi-Agentic System MAS Threat Modeling Guide, translating recent anticipatory research in multi-agent security MASEC into practical guidance for addressing challenges unique to large language model LLM-driven multi-agent architectures. Although OWASP's...
Exploit for Incorrect Authorization in Sudo_Project Sudo
sudo CVE-2025 Toolkit Unified scanner, benign proof-of-...
Who'S the Evil Twin? Differential Auditing for Undesired Behavior
Detecting hidden behaviors in neural networks poses a significant challenge due to minimal prior knowledge and potential adversarial obfuscation. We explore this problem by framing detection as an adversarial game between two teams: the red team trains two similar models, one trained solely on...