Can Transformer Memory Be Corrupted? Investigating Cache-Side Vulnerabilities in Large Language Models

Even when prompts and parameters are secured, transformer language models remain vulnerable because their key-value KV cache during inference constitutes an overlooked attack surface. This paper introduces Malicious Token Injection MTI, a modular framework that systematically perturbs cached key...

Cryptanalysis of a Privacy-Preserving Ride-Hailing Service from NSS 2022

Ride-Hailing Services RHS match a ride request initiated by a rider with a suitable driver responding to the ride request. A Privacy-Preserving RHS PP-RHS aims to facilitate ride matching while ensuring the privacy of riders' and drivers' location data w.r.t. the Service Provider SP. At NSS 2022,...

Feedback Lunch: Deep Feedback Codes for Wiretap Channels

We consider reversely-degraded wiretap channels, for which the secrecy capacity is zero if there is no channel feedback. This work focuses on a seeded modular code design for the Gaussian wiretap channel with channel output feedback, combining universal hash functions for security and learned...

Colliding with Adversaries at ECML-PKDD 2025 Adversarial Attack Competition 1st Prize Solution

This report presents the winning solution for Task 1 of Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics Discovery at ECML-PKDD 2025. The task required designing an adversarial attack against a provided classification model that maximizes misclassification while...

Toward Understanding Security Issues in the Model Context Protocol Ecosystem

The Model Context Protocol MCP is an emerging open standard that enables AI-powered applications to interact with external tools through structured metadata. A rapidly growing ecosystem has formed around MCP, including a wide range of MCP hosts i.e., Cursor, Windsurf, Claude Desktop, and Cline, M...

Structuring Security: A Survey of Cybersecurity Ontologies, Semantic Log Processing, and LLMs Application

This survey investigates how ontologies, semantic log processing, and Large Language Models LLMs enhance cybersecurity. Ontologies structure domain knowledge, enabling interoperability, data integration, and advanced threat analysis. Security logs, though critical, are often unstructured and...

$Ρ$Hammer: Reviving RowHammer Attacks on New Architectures Via Prefetching

Rowhammer is a critical vulnerability in dynamic random access memory DRAM that continues to pose a significant threat to various systems. However, we find that conventional load-based attacks are becoming highly ineffective on the most recent architectures such as Intel Alder and Raptor Lake. In...

Towards a Blockchain-Based CI/CD Framework to Enhance Security in Cloud Environments

Security is becoming a pivotal point in cloud platforms. Several divisions, such as business organisations, health care, government, etc., have experienced cyber-attacks on their infrastructures. This research focuses on security issues within Continuous Integration and Deployment CI/CD pipelines...

Don't Look Up: There Are Sensitive Internal Links in the Clear on GEO Satellites

Geosynchronous GEO satellite links provide IP backhaul to remote critical infrastructure for utilities, telecom, government, military, and commercial users. To date, academic studies of GEO infrastructure have focused on a handful of satellites and specific use cases. The authors of this paper...

When Intelligence Fails: An Empirical Study on Why LLMs Struggle with Password Cracking

The remarkable capabilities of Large Language Models LLMs in natural language understanding and generation have sparked interest in their potential for cybersecurity applications, including password guessing. In this study, we conduct an empirical investigation into the efficacy of pre-trained LL...

WebRTC Metadata and IP Leakage in Modern Browsers: A Cross-Platform Measurement Study

Web Real-Time Communication WebRTC enables real-time peer-to-peer communication, but its Interactive Connectivity Establishment ICE process can unintentionally expose internal and public IP addresses as metadata. This paper presents a cross-platform measurement study of WebRTC metadata leakage...

C/N0 Analysis-Based GPS Spoofing Detection with Variable Antenna Orientations

GPS spoofing poses a growing threat to aviation by falsifying satellite signals and misleading aircraft navigation systems. This paper demonstrates a proof-of-concept spoofing detection strategy based on analyzing satellite Carrier-to-Noise Density Ratio C/N$0$ variation during controlled static...

Towards Proactive Defense against Cyber Cognitive Attacks

Cyber cognitive attacks leverage disruptive innovations DIs to exploit psychological biases and manipulate decision-making processes. Emerging technologies, such as AI-driven disinformation and synthetic media, have accelerated the scale and sophistication of these threats. Prior studies primaril...

MalCVE: Malware Detection and CVE Association Using Large Language Models

Malicious software attacks are having an increasingly significant economic impact. Commercial malware detection software can be costly, and tools that attribute malware to the specific software vulnerabilities it exploits are largely lacking. Understanding the connection between malware and the...

SoK: Taxonomy and Evaluation of Prompt Security in Large Language Models

Large Language Models LLMs have rapidly become integral to real-world applications, powering services across diverse sectors. However, their widespread deployment has exposed critical security risks, particularly through jailbreak prompts that can bypass model alignment and induce harmful outputs...

Zeek 8.0.3

Zeek is a powerful network analysis framework that is much different from the typical IDS you may know. While focusing on network security monitoring, Zeek provides a comprehensive platform for more general network traffic analysis as well. Well grounded in more than 15 years of research, Zeek ha...

Active Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreaks

Large language models LLMs are increasingly vulnerable to multi-turn jailbreak attacks, where adversaries iteratively elicit harmful behaviors that bypass single-turn safety filters. Existing defenses predominantly rely on passive rejection, which either fails against adaptive attackers or overly...

PoTS: Proof-Of-Training-Steps for Backdoor Detection in Large Language Models

As Large Language Models LLMs gain traction across critical domains, ensuring secure and trustworthy training processes has become a major concern. Backdoor attacks, where malicious actors inject hidden triggers into training data, are particularly insidious and difficult to detect. Existing...

Improving Cybercrime Detection and Digital Forensics Investigations with Artificial Intelligence

According to a recent EUROPOL report, cybercrime is still recurrent in Europe, and different activities and countermeasures must be taken to limit, prevent, detect, analyze, and fight it. Cybercrime must be prevented with specific measures, tools, and techniques, for example through automated...

Intermittent File Encryption in Ransomware: Measurement, Modeling, and Detection

File encrypting ransomware increasingly employs intermittent encryption techniques, encrypting only parts of files to evade classical detection methods. These strategies, exemplified by ransomware families like BlackCat, complicate file structure based detection techniques due to diverse file...

Clam AntiVirus Toolkit 1.5.1

Clam AntiVirus is an anti-virus toolkit for Unix. The main purpose of this software is the integration with mail servers attachment scanning. The package provides a flexible and scalable multi-threaded daemon, a command-line scanner, and a tool for automatic updating via Internet. The programs ar...

LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?

Large language model LLM agents have demonstrated remarkable capabilities in software engineering and cybersecurity tasks, including code generation, vulnerability discovery, and automated testing. One critical but underexplored application is automated web vulnerability reproduction, which...

Leveraging Code Cohesion Analysis to Identify Source Code Supply Chain Attacks

Supply chain attacks significantly threaten software security with malicious code injections within legitimate projects. Such attacks are very rare but may have a devastating impact. Detecting spurious code injections using automated tools is further complicated as it often requires deciphering t...

Beyond a Single Perspective: Towards a Realistic Evaluation of Website Fingerprinting Attacks

Website Fingerprinting WF attacks exploit patterns in encrypted traffic to infer the websites visited by users, posing a serious threat to anonymous communication systems. Although recent WF techniques achieve over 90% accuracy in controlled experimental settings, most studies remain confined to...

AEX-NStep: Probabilistic Interrupt Counting Attacks on Intel SGX

To mitigate interrupt-based stepping attacks notably using SGX-Step, Intel introduced AEX-Notify, an ISA extension to Intel SGX that aims to prevent deterministic single-stepping. In this work, we introduce AEX-NStep, the first interrupt counting attack on AEX-Notify-enabled Enclaves. We show tha...

A Novel GPT-Based Framework for Anomaly Detection in System Logs

Identification of anomalous events within system logs constitutes a pivotal element within the frame- work of cybersecurity defense strategies. However, this process faces numerous challenges, including the management of substantial data volumes, the distribution of anomalies, and the precision o...

TITAN: Graph-Executable Reasoning for Cyber Threat Intelligence

TITAN Threat Intelligence Through Automated Navigation is a framework that connects natural-language cyber threat queries with executable reasoning over a structured knowledge graph. It integrates a path planner model, which predicts logical relation chains from text, and a graph executor that...

A Hard-Label Black-Box Evasion Attack against ML-Based Malicious Traffic Detection Systems

Machine Learning ML-based malicious traffic detection is a promising security paradigm. It outperforms rule-based traditional detection by identifying various advanced attacks. However, the robustness of these ML models is largely unexplored, thereby allowing attackers to craft adversarial traffi...

RoBCtrl: Attacking GNN-Based Social Bot Detectors Via Reinforced Manipulation of Bots Control Interaction

Social networks have become a crucial source of real-time information for individuals. The influence of social bots within these platforms has garnered considerable attention from researchers, leading to the development of numerous detection technologies. However, the vulnerability and robustness...

Toward Cybersecurity-Expert Small Language Models

Large language models LLMs are transforming everyday applications, yet deployment in cybersecurity lags due to a lack of high-quality, domain-specific models and training datasets. To address this gap, we present CyberPal 2.0, a family of cybersecurity-expert small language models SLMs ranging fr...

Infrastructure Patterns in Toll Scam Domains: A Comprehensive Analysis of Cybercriminal Registration and Hosting Strategies

Toll scams involve criminals registering fake domains that pretend to be legitimate transportation agencies to trick users into making fraudulent payments. Although these scams are rapidly increasing and causing significant harm, they have not been extensively studied. We present the first...

Securing U.S. Critical Infrastructure: Lessons from Stuxnet and the Ukraine Power Grid Attacks

Industrial Control Systems ICS underpin the United States' critical infrastructure, managing essential services such as power, water, and transportation that are vital to national security and public safety. However, increasing digital integration has exposed these systems to escalating cyber...

How Blind and Low-Vision Users Manage Their Passwords

Managing passwords securely and conveniently is still an open problem for many users. Existing research has examined users' password management strategies and identified pain points, such as security concerns, leading to insecure practices. We investigate how Blind and Low-Vision BLV users tackle...

In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers

Large Language Model LLM based agents integrated into web browsers often called agentic AI browsers offer powerful automation of web tasks. However, they are vulnerable to indirect prompt injection attacks, where malicious instructions hidden in a webpage deceive the agent into unwanted actions...

GRIDAI: Generating and Repairing Intrusion Detection Rules Via Collaboration among Multiple LLM-Based Agents

Rule-based network intrusion detection systems play a crucial role in the real-time detection of Web attacks. However, most existing works primarily focus on automatically generating detection rules for new attacks, often overlooking the relationships between new attacks and existing rules, which...

Power Grid Cybersecurity: Policy Analysis White Paper

The U.S. power grid underpins national security, public safety, and economic stability, but faces growing cyber risks from vulnerabilities in industrial control systems, remote access, and poor cyber hygiene. Despite its critical importance, current policy remains fragmented and reactive. This...

Injection, Attack and Erasure: Revocable Backdoor Attacks Via Machine Unlearning

Backdoor attacks pose a persistent security risk to deep neural networks DNNs due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack strategies still leave persistent traces that may be detect...

Multi-Copy Security in Unclonable Cryptography

Unclonable cryptography leverages the quantum no-cloning principle to copy-protect cryptographic functionalities. While most existing works address the basic single-copy security, the stronger notion of multi-copy security remains largely unexplored. We introduce a generic compiler that upgrades...

HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities

Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem. While language model agents show promise in cybersecurity, moder...

Wapiti Web Application Vulnerability Scanner 3.2.7 Source Code

Wapiti is a web application vulnerability scanner. It will scan the web pages of a deployed web application and will fuzz the URL parameters and forms to find common web vulnerabilities. This is the source code release...

DeepTrust: Multi-Step Classification through Dissimilar Adversarial Representations for Robust Android Malware Detection

Over the last decade, machine learning has been extensively applied to identify malicious Android applications. However, such approaches remain vulnerable against adversarial examples, i.e., examples that are subtly manipulated to fool a machine learning model into making incorrect predictions...

Noisy Neighbor: Exploiting RDMA for Resource Exhaustion Attacks in Containerized Clouds

In modern containerized cloud environments, the adoption of RDMA Remote Direct Memory Access has expanded to reduce CPU overhead and enable high-performance data exchange. Achieving this requires strong performance isolation to ensure that one container's RDMA workload does not degrade the...

PromoGuardian: Detecting Promotion Abuse Fraud with Multi-Relation Fused Graph Neural Networks

As e-commerce platforms develop, fraudulent activities are increasingly emerging, posing significant threats to the security and stability of these platforms. Promotion abuse is one of the fastest-growing types of fraud in recent years and is characterized by users exploiting promotional activiti...

Targeted Pooled Latent-Space Steganalysis Applied to Generative Steganography, with a Fix

Steganographic schemes dedicated to generated images modify the seed vector in the latent space to embed a message, whereas most steganalysis methods attempt to detect the embedding in the image space. This paper proposes to perform steganalysis in the latent space by modeling the statistical...

ShuffleV: A Microarchitectural Defense Strategy against Electromagnetic Side-Channel Attacks in Microprocessors

The run-time electromagnetic EM emanation of microprocessors presents a side-channel that leaks the confidentiality of the applications running on them. Many recent works have demonstrated successful attacks leveraging such side-channels to extract the confidentiality of diverse applications, suc...

PromptLocate: Localizing Prompt Injection Attacks

Prompt injection attacks deceive a large language model into completing an attacker-specified task instead of its intended task by contaminating its input data with an injected prompt, which consists of injected instructions and data. Localizing the injected prompt within contaminated data is...

From Misinformation to Climate Crisis: Navigating Vulnerabilities in the Cyber-Physical-Social Systems

Within the cyber-physical-social-climate nexus, all systems are deeply interdependent: cyber infrastructure facilitates communication, data processing, and automation across physical systems such as power grids and networks, while social infrastructure provides the human capital and societal norm...

Wapiti Web Application Vulnerability Scanner 3.2.7

Wapiti is a web application vulnerability scanner. It will scan the web pages of a deployed web application and will fuzz the URL parameters and forms to find common web vulnerabilities. This is the binary release...

Pixnapping: Bringing Pixel Stealing out of the Stone Age

Pixel stealing attacks enable malicious websites to leak sensitive content displayed in victim websites. The idea, introduced by Stone in 2013, is to embed victim websites in iframes and use SVG filters to compute on, and create side channels as a function of, those websites' pixels. Fortunately,...

Breaking Guardrails, Facing Walls: Insights on Adversarial AI for Defenders and Researchers

Analyzing 500 CTF participants, this paper shows that while participants readily bypassed simple AI guardrails using common techniques, layered multi-step defenses still posed significant challenges, offering concrete insights for building safer AI systems...