Chasing Shadows: Pitfalls in LLM Security Research

Large language models LLMs are increasingly prevalent in security research. Their unique characteristics, however, introduce challenges that undermine established paradigms of reproducibility, rigor, and evaluation. Prior work has identified common pitfalls in traditional machine learning researc...

Information-Dense Reasoning for Efficient and Auditable Security Alert Triage

Security Operations Centers face massive, heterogeneous alert streams under minute-level service windows, creating the Alert Triage Latency Paradox: verbose reasoning chains ensure accuracy and compliance but incur prohibitive latency and token costs, while minimal chains sacrifice transparency a...

Exploit for OS Command Injection in Gnu Bash

Exploiting Shellshock CVE-2014-6271: A Complete, Modern Demo...

Exploit for CVE-2025-55182

React2Shell Vulnerable Banking Application Lab Deliberately v...

One Detector Fits All: Robust and Adaptive Detection of Malicious Packages from PyPI to Enterprises

The rise of supply chain attacks via malicious Python packages demands robust detection solutions. Current approaches, however, overlook two critical challenges: robustness against adversarial source code transformations and adaptability to the varying false positive rate FPR requirements of...

Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models

Whitepaper from researchers at MIT, Northeastern University, and Meta. For an LLM to correctly respond to an instruction it must understand both the semantics and the domain i.e., subject area of a given task-instruction pair. However, syntax can also convey implicit information Recent work shows...

Exposing Vulnerabilities in RL: A Novel Stealthy Backdoor Attack through Reward Poisoning

Reinforcement learning RL has achieved remarkable success across diverse domains, enabling autonomous systems to learn and adapt to dynamic environments by optimizing a reward function. However, this reliance on reward signals creates a significant security vulnerability. In this paper, we study ...

Department-Specific Security Awareness Campaigns: A Cross-Organizational Study of HR and Accounting

Many cyberattacks succeed because they exploit flaws at the human level. To address this problem, organizations rely on security awareness programs, which aim to make employees more resilient against social engineering. While some works have suggested that such programs should account for...

An Efficient Privacy-Preserving Intrusion Detection Scheme for UAV Swarm Networks

The rapid proliferation of unmanned aerial vehicles UAVs and their applications in diverse domains, such as surveillance, disaster management, agriculture, and defense, have revolutionized modern technology. While the potential benefits of swarm-based UAV networks are growing significantly, they...

HarmonicAttack: An Adaptive Cross-Domain Audio Watermark Removal

The availability of high-quality, AI-generated audio raises security challenges such as misinformation campaigns and voice-cloning fraud. A key defense against the misuse of AI-generated audio is by watermarking it, so that it can be easily distinguished from genuine audio. As those seeking to...

Accuracy and Efficiency Trade-Offs in LLM-Based Malware Detection and Explanation: A Comparative Study of Parameter Tuning Vs. Full Fine-Tuning

This study examines whether Low-Rank Adaptation LoRA fine-tuned Large Language Models LLMs can approximate the performance of fully fine-tuned models in generating human-interpretable decisions and explanations for malware classification. Achieving trustworthy malware detection, particularly when...

AutoGraphAD: A Novel Approach Using Variational Graph Autoencoders for Anomalous Network Flow Detection

Network Intrusion Detection Systems NIDS are essential tools for detecting network attacks and intrusions. While extensive research has explored the use of supervised Machine Learning for attack detection and characterisation, these methods require accurately labelled datasets, which are very...

[Correction] Gmail can read your emails and attachments to power “smart features”

Update November 22. We’ve updated this article after realising we contributed to a perfect storm of misunderstanding around a recent change in the wording and placement of Gmail's smart features. The settings themselves aren’t new, but the way Google recently rewrote and surfaced them led a lot o...

Explainable Transformer-Based Email Phishing Classification with Adversarial Robustness

Phishing and related cyber threats are becoming more varied and technologically advanced. Among these, email-based phishing remains the most dominant and persistent threat. These attacks exploit human vulnerabilities to disseminate malware or gain unauthorized access to sensitive information. Dee...

Adaptive Intrusion Detection for Evolving RPL IoT Attacks Using Incremental Learning

The routing protocol for low-power and lossy networks RPL has become the de facto routing standard for resource-constrained IoT systems, but its lightweight design exposes critical vulnerabilities to a wide range of routing-layer attacks such as hello flood, decreased rank, and version number...

Phantom Menace: Exploring and Enhancing the Robustness of VLA Models against Physical Sensor Attacks

Vision-Language-Action VLA models revolutionize robotic systems by enabling end-to-end perception-to-action pipelines that integrate multiple sensory modalities, such as visual signals processed by cameras and auditory signals captured by microphones. This multi-modality integration allows VLA...

Taught by the Flawed: How Dataset Insecurity Breeds Vulnerable AI Code

AI programming assistants have demonstrated a tendency to generate code containing basic security vulnerabilities. While developers are ultimately responsible for validating and reviewing such outputs, improving the inherent quality of these generated code snippets remains essential. A key...

NVIDIA Megatron-LM 代码注入漏洞

NVIDIA Megatron-LM is a PyTorch-based distributed training framework from NVIDIA that is specifically designed for training large Transformer language models. NVIDIA Megatron-LM suffers from a code injection vulnerability that stems from scripts improperly handling malicious data, which could lea...

​​Securing our future: November 2025 progress report on Microsoft’s Secure Future Initiative ​​

When we launched the Secure Future Initiative SFI, our mission was clear: accelerate innovation, strengthen resilience, and lead the industry toward a safer digital future. Today, we’re sharing our latest progress report that reflects steady progress in every area and engineering pillar,...

Adversarially Robust and Interpretable Magecart Malware Detection

Magecart skimming attacks have emerged as a significant threat to client-side security and user trust in online payment systems. This paper addresses the challenge of achieving robust and explainable detection of Magecart attacks through a comparative study of various Machine Learning ML models...