BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-To-Image Diffusion Models

In recent years,Diffusion models have achieved remarkable progress in the field of image generation.However,recent studies have shown that diffusion models are susceptible to backdoor attacks,in which attackers can manipulate the output by injecting covert triggers such as specific visual pattern...

Evaluating Software Supply Chain Security in Research Software

The security of research software is essential for ensuring the integrity and reproducibility of scientific results. However, research software security is still largely unexplored. Due to its dependence on open source components and distributed development practices, research software is...

When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

As large language models become increasingly integrated into daily life, audio has emerged as a key interface for human-AI interaction. However, this convenience also introduces new vulnerabilities, making audio a potential attack surface for adversaries. Our research introduces WhisperInject, a...

BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS

In this paper, we endeavor to address the challenges of backdoor attacks countermeasures in black-box scenarios, thereby fortifying the security of inference under MLaaS. We first categorize backdoor triggers from a new perspective, i.e., their impact on the patched area, and divide them into:...

Simulating Cyberattacks through a Breach Attack Simulation (BAS) Platform Empowered by Security Chaos Engineering (SCE)

In today digital landscape, organizations face constantly evolving cyber threats, making it essential to discover slippery attack vectors through novel techniques like Security Chaos Engineering SCE, which allows teams to test defenses and identify vulnerabilities effectively. This paper proposes...

From Legacy to Standard: LLM-Assisted Transformation of Cybersecurity Playbooks into CACAO Format

Existing cybersecurity playbooks are often written in heterogeneous, non-machine-readable formats, which limits their automation and interoperability across Security Orchestration, Automation, and Response platforms. This paper explores the suitability of Large Language Models, combined with Prom...

Linux 6.9 AF_UNIX MSG_OOB Handling Use-After-Free

Linux versions starting at 6.9 have a security bug in the handling of MSGOOB, which causes use-after-free read+write when a sequence of syscalls is executed...

Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools

Large language model LLM agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface: adversaries can manipulate tool metadata -- such as names,...

Secure MmWave Beamforming with Proactive-ISAC Defense against Beam-Stealing Attacks

Millimeter-wave mmWave communication systems face increasing susceptibility to advanced beam-stealing attacks, posing a significant physical layer security threat. This paper introduces a novel framework employing an advanced Deep Reinforcement Learning DRL agent for proactive and adaptive defens...

LMDG: Advancing Lateral Movement Detection through High-Fidelity Dataset Generation

Lateral Movement LM attacks continue to pose a significant threat to enterprise security, enabling adversaries to stealthily compromise critical assets. However, the development and evaluation of LM detection systems are impeded by the absence of realistic, well-labeled datasets. To address this...

Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM As a Judge, and a Lightweight CTF Benchmark

Recent advances in LLM agentic systems have improved the automation of offensive security tasks, particularly for Capture the Flag CTF challenges. We systematically investigate the key factors that drive agent success and provide a detailed recipe for building effective LLM-based offensive securi...

PentestJudge: Judging Agent Behavior against Operational Requirements

We introduce PentestJudge, a system for evaluating the operations of penetration testing agents. PentestJudge is a large language model LLM-as-judge with access to tools that allow it to consume arbitrary trajectories of agent states and tool call history to determine whether a security agent's...

Centralized Dynamic State Estimation Algorithm for Detecting and Distinguishing Faults and Cyber Attacks in Power Systems

As power systems evolve with increased integration of renewable energy sources, they become more complex and vulnerable to both cyber and physical threats. This study validates a centralized Dynamic State Estimation DSE algorithm designed to enhance the protection of power systems, particularly...

LPAR2RRD Remote Code Execution

This repository contains a proof of concept exploit for CVE-2025-54769, a vulnerability found in lpar2rrd. The vulnerability allows remote code execution and directory traversal by abusing the /lpar2rrd-cgi/upgrade.sh endpoint...

SUAD: Solid-Channel Ultrasound Injection Attack and Defense to Voice Assistants

As a versatile AI application, voice assistants VAs have become increasingly popular, but are vulnerable to security threats. Attackers have proposed various inaudible attacks, but are limited by cost, distance, or LoS. Therefore, we propose \nameAttack, a long-range, cross-barrier, and...

PhishParrot: LLM-Driven Adaptive Crawling to Unveil Cloaked Phishing Sites

Phishing attacks continue to evolve, with cloaking techniques posing a significant challenge to detection efforts. Cloaking allows attackers to display phishing sites only to specific users while presenting legitimate pages to security crawlers, rendering traditional detection systems ineffective...

Gandia Integra Total 4.4.2236.1 SQL Injection

Gandia Integra Total versions 2.1.2217.3 through 4.4.2236.1 suffer from a remote SQL injection vulnerability...

WordPress Alone Theme 7.8.3 Arbitrary Plugin Upload

WordPress Alone Theme versions 7.8.3 and below suffer from an arbitrary plugin upload vulnerability...

Copyparty 1.18.6 Cross Site Scripting

Copyparty versions 1.18.6 and below suffer from a cross site scripting vulnerability...

Swagger UI 1.0.3 Cross Site Scripting

Proof of concept cross site scripting exploit for Swagger UI versions 1.0.3 and below...

ASINT: Learning AS-To-Organization Mapping from Internet Metadata

Accurately mapping Autonomous Systems ASNs to their owning or operating organizations underpins Internet measurement research and security applications. Yet existing approaches commonly rely solely on WHOIS or PeeringDB, missing important relationships e.g., cross-regional aliases, parent-child...

Hashcat Advanced Password Recovery 7.0.0 Binary Release

Hashcat is an advanced GPU hash cracking utility that includes the World's fastest md5crypt, phpass, mscash2 and WPA / WPA2 cracker. It also has the first and only GPGPU-based rule engine, focuses on highly iterated modern hashes, single dictionary-based attacks, and more. This is the binary...

The Dark Side of Upgrades: Uncovering Security Risks in Smart Contract Upgrades

Smart contract upgrades are increasingly common due to their flexibility in modifying deployed contracts, such as fixing bugs or adding new functionalities. Meanwhile, upgrades compromise the immutability of contracts, introducing significant security concerns. While existing research has explore...

Coward: toward Practical Proactive Federated Backdoor Defense Via Collision-Based Watermark

Backdoor detection is currently the mainstream defense against backdoor attacks in federated learning FL, where malicious clients upload poisoned updates that compromise the global model and undermine the reliability of FL deployments. Existing backdoor detection techniques fall into two...

DINA: a Dual Defense Framework against Internal Noise and External Attacks in Natural Language Processing

As large language models LLMs and generative AI become increasingly integrated into customer service and moderation applications, adversarial threats emerge from both external manipulations and internal label corruption. In this work, we identify and systematically address these dual adversarial...

Experimental Evaluation of Post-Quantum Homomorphic Encryption for Privacy-Preserving V2X Communication

Intelligent Transportation Systems ITS fundamentally rely on vehicle-generated data for applications such as congestion monitoring and route optimization, making the preservation of user privacy a critical challenge. Homomorphic Encryption HE offers a promising solution by enabling computation on...

A Survey on Data Security in Large Language Models

Large Language Models LLMs, now a foundation in advancing natural language processing, power applications such as text generation, machine translation, and conversational systems. Despite their transformative potential, these models inherently rely on massive amounts of training data, often...

WordPress Alone Theme 7.8.3 Arbitrary Plugin Upload / Code Execution

WordPress Alone Theme versions 7.8.3 and below are vulnerable to an unauthenticated arbitrary file upload vulnerability. This flaw allows unauthenticated attackers to upload and install arbitrary plugin ZIP files from remote URLs via an unprotected AJAX endpoint — resulting in remote code executi...

Microsoft Edge Information Disclosure

Microsoft Edge Chromium-based suffers from an information disclosure vulnerability...

Can LLMs Effectively Provide Game-Theoretic-Based Scenarios for Cybersecurity?

Game theory has long served as a foundational tool in cybersecurity to test, predict, and design strategic interactions between attackers and defenders. The recent advent of Large Language Models LLMs offers new tools and challenges for the security of computer systems; In this work, we investiga...

WordPress Sala Theme 1.1.4 Privilege Escalation

WordPress Sala Theme versions 1.1.4 and below are vulnerable to an unauthenticated privilege escalation vulnerability. This flaw allows unauthenticated attackers to reset passwords of arbitrary users — including administrators — by directly invoking an exposed AJAX endpoint without verifying the...

Real-World Evaluation of Protocol-Compliant Denial-Of-Service Attacks on C-V2X-Based Forward Collision Warning Systems

Cellular Vehicle-to-Everything C-V2X technology enables low-latency, reliable communications essential for safety applications such as a Forward Collision Warning FCW system. C-V2X deployments operate under strict protocol compliance with the 3rd Generation Partnership Project 3GPP and the Societ...

Thwart Me If You Can: an Empirical Analysis of Android Platform Armoring against Stalkerware

Stalkerware is a serious threat to individuals' privacy that is receiving increased attention from the security and privacy research communities. Existing works have largely focused on studying leading stalkerware apps, dual-purpose apps, monetization of stalkerware, or the experience of survivor...

Whispering Agents: an Event-Driven Covert Communication Protocol for the Internet of Agents

The emergence of the Internet of Agents IoA introduces critical challenges for communication privacy in sensitive, high-stakes domains. While standard Agent-to-Agent A2A protocols secure message content, they are not designed to protect the act of communication itself, leaving agents vulnerable t...

Large Reasoning Models Are Autonomous Jailbreak Agents

Jailbreaking -- bypassing built-in safety mechanisms in AI models -- has traditionally required complex technical procedures or specialized human expertise. In this study, we show that the persuasive capabilities of large reasoning models LRMs simplify and scale jailbreaking, converting it into a...

A Survey on Privacy-Preserving Computing in the Automotive Domain

As vehicles become increasingly connected and autonomous, they accumulate and manage various personal data, thereby presenting a key challenge in preserving privacy during data sharing and processing. This survey reviews applications of Secure Multi-Party Computation MPC and Homomorphic Encryptio...

Semantic Encryption: Secure and Effective Interaction with Cloud-Based Large Language Models Via Semantic Transformation

The increasing adoption of Cloud-based Large Language Models CLLMs has raised significant concerns regarding data privacy during user interactions. While existing approaches primarily focus on encrypting sensitive information, they often overlook the logical structure of user inputs. This oversig...

BeDKD: Backdoor Defense Based on Dynamic Knowledge Distillation and Directional Mapping Modulator

Although existing backdoor defenses have gained success in mitigating backdoor attacks, they still face substantial challenges. In particular, most of them rely on large amounts of clean data to weaken the backdoor mapping but generally struggle with residual trigger effects, resulting in...

PRIME: Plasticity-Robust Incremental Model for Encrypted Traffic Classification in Dynamic Network Environments

With the continuous development of network environments and technologies, ensuring cyber security and governance is increasingly challenging. Network traffic classificationETC can analyzes attributes such as application categories and malicious intent, supporting network management services like...

Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense

Deep neural networks DNNs and generative AI GenAI are increasingly vulnerable to backdoor attacks, where adversaries embed triggers into inputs to cause models to misclassify or misinterpret target labels. Beyond traditional single-trigger scenarios, attackers may inject multiple triggers across...

Complete Evasion, Zero Modification: PDF Attacks on AI Text Detection

AI-generated text detectors have become essential tools for maintaining content authenticity, yet their robustness against evasion attacks remains questionable. We present PDFuzz, a novel attack that exploits the discrepancy between visual text layout and extraction order in PDF documents. Our...

Hard-Earned Lessons in Access Control at Scale: Enforcing Identity and Policy across Trust Boundaries with Reverse Proxies and MTLS

In today's enterprise environment, traditional access methods such as Virtual Private Networks VPNs and application-specific Single Sign-On SSO often fall short when it comes to securely scaling access for a distributed and dynamic workforce. This paper presents our experience implementing a...

Beyond Vulnerabilities: a Survey of Adversarial Attacks As Both Threats and Defenses in Computer Vision Systems

Adversarial attacks against computer vision systems have emerged as a critical research area that challenges the fundamental assumptions about neural network robustness and security. This comprehensive survey examines the evolving landscape of adversarial techniques, revealing their dual nature a...

GPU in the Blind Spot: Overlooked Security Risks in Transportation

Graphics processing units GPUs are becoming an essential part of the intelligent transportation system ITS for enabling video-based and artificial intelligence AI based applications. GPUs provide high-throughput and energy-efficient computing for tasks like sensor fusion and roadside video...

"Energon": Unveiling Transformers from GPU Power and Thermal Side-Channels

Transformers have become the backbone of many Machine Learning ML applications, including language translation, summarization, and computer vision. As these models are increasingly deployed in shared Graphics Processing Unit GPU environments via Machine Learning as a Service MLaaS, concerns aroun...

LLM-Assisted Model-Based Fuzzing of Protocol Implementations

Testing network protocol implementations is critical for ensuring the reliability, security, and interoperability of distributed systems. Faults in protocol behavior can lead to vulnerabilities and system failures, especially in real-time and mission-critical applications. A common approach to...

DUP: Detection-Guided Unlearning for Backdoor Purification in Language Models

As backdoor attacks become more stealthy and robust, they reveal critical weaknesses in current defense strategies: detection methods often rely on coarse-grained feature statistics, and purification methods typically require full retraining or additional clean models. To address these challenges...

A Provably Secure Network Protocol for Private Communication with Analysis and Tracing Resistance

Anonymous communication networks have emerged as crucial tools for obfuscating communication pathways and concealing user identities. However, their practical deployments face significant challenges, including susceptibility to artificial intelligence AI-powered metadata analysis, difficulties in...

Generative AI-Empowered Secure Communications in Space-Air-Ground Integrated Networks: a Survey and Tutorial

Space-air-ground integrated networks SAGINs face unprecedented security challenges due to their inherent characteristics, such as multidimensional heterogeneity and dynamic topologies. These characteristics fundamentally undermine conventional security methods and traditional artificial...

IMU: Influence-Guided Machine Unlearning

Recent studies have shown that deep learning models are vulnerable to attacks and tend to memorize training data points, raising significant concerns about privacy leakage. This motivates the development of machine unlearning MU, i.e., a paradigm that enables models to selectively forget specific...