Can MLLMs Detect Phishing? A Comprehensive Security Benchmark Suite Focusing on Dynamic Threats and Multimodal Evaluation in Academic Environments

The rapid proliferation of Multimodal Large Language Models MLLMs has introduced unprecedented security challenges, particularly in phishing detection within academic environments. Academic institutions and researchers are high-value targets, facing dynamic, multilingual, and context-dependent...

Securing AI Agents against Prompt Injection Attacks

Retrieval-augmented generation RAG systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive benchmark for evaluating prompt injection risks in RAG-enabled A...

LFreeDA: Label-Free Drift Adaptation for Windows Malware Detection

Machine learning ML-based malware detectors degrade over time as concept drift introduces new and evolving families unseen during training. Retraining is limited by the cost and time of manual labeling or sandbox analysis. Existing approaches mitigate this via drift detection and selective...

Beyond Fixed and Dynamic Prompts: Embedded Jailbreak Templates for Advancing LLM Security

As the use of large language models LLMs continues to expand, ensuring their safety and robustness has become a critical challenge. In particular, jailbreak attacks that bypass built-in safety mechanisms are increasingly recognized as a tangible threat across industries, driving the need for...

Adaptive Dual-Layer Web Application Firewall (ADL-WAF) Leveraging Machine Learning for Enhanced Anomaly and Threat Detection

Web Application Firewalls are crucial for protecting web applications against a wide range of cyber threats. Traditional Web Application Firewalls often struggle to effectively distinguish between malicious and legitimate traffic, leading to limited efficacy in threat detection. To overcome these...

PATCHEVAL: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities

Software vulnerabilities are increasing at an alarming rate. However, manual patching is both time-consuming and resource-intensive, while existing automated vulnerability repair AVR techniques remain limited in effectiveness. Recent advances in large language models LLMs have opened a new paradi...

EUVD-2025-176379

Malicious code in signal-star-benchmark-report-small npm...

EUVD-2025-177410

Malicious code in orchestrate-benchmark-spy-air-cat npm...

MAL-2025-189693 Malicious code in string-container-benchmark-phi-cat (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c8eeddb7aaf4eb14b9f84cab9ef4d5c482fe254563dc9dfb921f8ee860c3b659 This package appears to be part of the tea.xyz token reward campaign that flooded npm. These packages typically contain autopublish scripts auto.js,...

EUVD-2025-180104

Malicious code in benchmark-view-mu-cat-virtualize npm...

EUVD-2025-180105

Malicious code in benchmark-refactor-secure-scale-array npm...

EUVD-2025-177320

Malicious code in parse-abstract-beta-rain-benchmark npm...

EUVD-2025-180322

Malicious code in array-benchmark-socket-dog-fork npm...

EUVD-2025-175867

Malicious code in try-benchmark-assert-module-protected npm...

EUVD-2025-178450

Malicious code in import-benchmark-warn-node-catch npm...

EUVD-2025-178206

Malicious code in kernel-encode-benchmark-interface-virtualize npm...

EUVD-2025-179090

Malicious code in epsilon-protected-reject-parse-benchmark npm...

EUVD-2025-179252

Malicious code in double-benchmark-pipe-hash-virtualize npm...

EUVD-2025-176530

Malicious code in sanitize-analyze-benchmark-deploy-encode npm...

EUVD-2025-176183

Malicious code in string-compile-module-benchmark-report npm...