AUTOPSY: a Framework for Tackling Privacy Challenges in the Automotive Industry

With the General Data Protection Regulation GDPR in place, all domains have to ensure compliance with privacy legislation. However, compliance does not necessarily result in a privacy-friendly system as for example getting users' consent to process their data does not improve the...

Towards Trustworthy AI: Secure Deepfake Detection Using CNNs and Zero-Knowledge Proofs

In the era of synthetic media, deepfake manipulations pose a significant threat to information integrity. To address this challenge, we propose TrustDefender, a two-stage framework comprising i a lightweight convolutional neural network CNN that detects deepfake imagery in real-time extended...

Zeek 7.0.9

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...

GATEBLEED: Exploiting On-Core Accelerator Power Gating for High Performance and Stealthy Attacks on AI

As power consumption from AI training and inference continues to increase, AI accelerators are being integrated directly into the CPU. Intel's Advanced Matrix Extensions AMX is one such example, debuting on the 4th generation Intel Xeon Scalable CPU. We discover a timing side and covert channel,...

ShrinkBox: Backdoor Attack on Object Detection to Disrupt Collision Avoidance in Machine Learning-Based Advanced Driver Assistance Systems

Advanced Driver Assistance Systems ADAS significantly enhance road safety by detecting potential collisions and alerting drivers. However, their reliance on expensive sensor technologies such as LiDAR and radar limits accessibility, particularly in low- and middle-income countries. Machine...

LENS-DF: Deepfake Detection and Temporal Localization for Long-Form Noisy Speech

This study introduces LENS-DF, a novel and comprehensive recipe for training and evaluating audio deepfake detection and temporal localization under complicated and realistic audio conditions. The generation part of the recipe outputs audios from the input dataset with several critical...

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage

Model compression is crucial for minimizing memory storage and accelerating inference in deep learning DL models, including recent foundation models like large language models LLMs. Users can access different compressed model versions according to their resources and budget. However, while existi...

EX-NIDS: a Framework for Explainable Network Intrusion Detection Leveraging Large Language Models

This paper introduces eX-NIDS, a framework designed to enhance interpretability in flow-based Network Intrusion Detection Systems NIDS by leveraging Large Language Models LLMs. In our proposed framework, flows labelled as malicious by NIDS are initially processed through a module called the Promp...

SharePoint CVE-2025-53770 Scanner

This is a scanner for the SharePoint unauthenticated remote code execution vulnerability, assigned CVE number CVE-2025-53770. The code for this was written by reverse-engineering a payload seen in the wild...

SoK: Securing the Final Frontier for Cybersecurity in Space-Based Infrastructure

With the advent of modern technology, critical infrastructure, communications, and national security depend increasingly on space-based assets. These assets, along with associated assets like data relay systems and ground stations, are, therefore, in serious danger of cyberattacks. Strong securit...

Building a Robust OAuth Token Based API Security: a High Level Overview

APIs Application Programming Interfaces or Web Services are the foundational building blocks that enable interconnected systems. However this proliferation of APIs has also introduced security challenges that require systematic and scalable solutions for secure authentication and authorization...

Logwatch 7.13

Logwatch analyzes and reports on unix system logs. It is a customizable and pluggable log monitoring system which will go through the logs for a given period of time and make a customizable report. It should work right out of the package on most systems...

Faraday 5.15.2

Faraday is a tool that introduces a new concept called IPE, or Integrated Penetration-Test Environment. It is a multiuser penetration test IDE designed for distribution, indexation and analysis of the generated data during the process of a security audit. The main purpose of Faraday is to re-use...

From Text to Actionable Intelligence: Automating STIX Entity and Relationship Extraction

Sharing methods of attack and their effectiveness is a cornerstone of building robust defensive systems. Threat analysis reports, produced by various individuals and organizations, play a critical role in supporting security operations and combating emerging threats. To enhance the timeliness and...

The Postman: a Journey of Ethical Hacking in PosteID/SPID Borderland

This paper presents a vulnerability assessment activity that we carried out on PosteID, the implementation of the Italian Public Digital Identity System SPID by Poste Italiane. The activity led to the discovery of a critical privilege escalation vulnerability, which was eventually patched. The...

Talking like a Phisher: LLM-Based Attacks on Voice Phishing Classifiers

Voice phishing vishing remains a persistent threat in cybersecurity, exploiting human trust through persuasive speech. While machine learning ML-based classifiers have shown promise in detecting malicious call transcripts, they remain vulnerable to adversarial manipulations that preserve semantic...

LLM4MEA: Data-Free Model Extraction Attacks on Sequential Recommenders Via Large Language Models

Recent studies have demonstrated the vulnerability of sequential recommender systems to Model Extraction Attacks MEAs. MEAs collect responses from recommender systems to replicate their functionality, enabling unauthorized deployments and posing critical privacy and security risks. Black-box...

LLMxCPG: Context-Aware Vulnerability Detection through Code Property Graph-Guided Large Language Models

Software vulnerabilities present a persistent security challenge, with over 25,000 new vulnerabilities reported in the Common Vulnerabilities and Exposures CVE database in 2024 alone. While deep learning based approaches show promise for vulnerability detection, recent studies reveal critical...

Revisiting Pre-Trained Language Models for Vulnerability Detection

The rapid advancement of pre-trained language models PLMs has demonstrated promising results for various code-related tasks. However, their effectiveness in detecting real-world vulnerabilities remains a critical challenge. % for the security community. While existing empirical studies evaluate...

Cyber Security of Mega Events: a Case Study of Securing the Digital Infrastructure for MahaKumbh 2025 -- a 45 Days Mega Event of 600 Million Footfalls

Mega events such as the Olympics, World Cup tournaments, G-20 Summit, religious events such as MahaKumbh are increasingly digitalized. From event ticketing, vendor booth or lodging reservations, sanitation, event scheduling, customer service, crime reporting, media streaming and messaging on...

In-Context Learning of Vision Language Models for Detection of Physical and Digital Attacks against Face Recognition Systems

Recent advances in biometric systems have significantly improved the detection and prevention of fraudulent activities. However, as detection methods improve, attack techniques become increasingly sophisticated. Attacks on face recognition systems can be broadly divided into physical and digital...

Pulse-Level Simulation of Crosstalk Attacks on Superconducting Quantum Hardware

Hardware crosstalk in multi-tenant superconducting quantum computers poses a severe security threat, allowing adversaries to induce targeted errors across tenant boundaries by injecting carefully engineered pulses. We present a simulation-based study of active crosstalk attacks at the pulse level...

Realistic Vulnerabilities of Decoy-State Quantum Key Distribution

We analyze realistic vulnerabilities of decoy-state quantum key distribution QKD arising from the combination of laser damage attack LDA and unambiguous state discrimination USD. While decoy-state QKD is designed to protect against photon-number-splitting and beam-splitting attacks by accurately...

SynthCTI: LLM-Driven Synthetic CTI Generation to Enhance MITRE Technique Mapping

Cyber Threat Intelligence CTI mining involves extracting structured insights from unstructured threat data, enabling organizations to understand and respond to evolving adversarial behavior. A key task in CTI mining is mapping threat descriptions to MITRE ATT&CK techniques. However, this process...

Optimizing Canaries for Privacy Auditing with Metagradient Descent

In this work we study black-box privacy auditing, where the goal is to lower bound the privacy parameter of a differentially private learning algorithm using only the algorithm's outputs i.e., final trained model. For DP-SGD the most successful method for training differentially private deep...

Attacking Interpretable NLP Systems

Studies have shown that machine learning systems are vulnerable to adversarial examples in theory and practice. Where previous attacks have focused mainly on visual models that exploit the difference between human and machine perception, text-based models have also fallen victim to these attacks...

FaultLine: Automated Proof-Of-Vulnerability Generation Using LLM Agents

Despite the critical threat posed by software security vulnerabilities, reports are often incomplete, lacking the proof-of-vulnerability PoV tests needed to validate fixes and prevent regressions. These tests are crucial not only for ensuring patches work, but also for helping developers understa...

Scaling Decentralized Learning with FLock

Fine-tuning the large language models LLMs are prevented by the deficiency of centralized control and the massive computing and communication overhead on the decentralized schemes. While the typical standard federated learning FL supports data privacy, the central server requirement creates a...

Liner Insecure Direct Object Reference / Brute Force

Liner is a reliable AI search engine with over 10 million users worldwide. It is vulnerable to an insecure direct object reference vulnerability. Conversation histories for all users are stored on the server. However, Liner's server does not distinguish the ownership or sharing status of individu...

MFAz: Historical Access Based Multi-Factor Authorization

Unauthorized access remains one of the critical security challenges in the realm of cybersecurity. With the increasing sophistication of attack techniques, the threat of unauthorized access is no longer confined to the conventional ones, such as exploiting weak access control policies. Instead,...

PhishIntentionLLM: Uncovering Phishing Website Intentions through Multi-Agent Retrieval-Augmented Generation

Phishing websites remain a major cybersecurity threat, yet existing methods primarily focus on detection, while the recognition of underlying malicious intentions remains largely unexplored. To address this gap, we propose PhishIntentionLLM, a multi-agent retrieval-augmented generation RAG...

BACFuzz: Exposing the Silence on Broken Access Control Vulnerabilities in Web Applications

Broken Access Control BAC remains one of the most critical and widespread vulnerabilities in web applications, allowing attackers to access unauthorized resources or perform privileged actions. Despite its severity, BAC is underexplored in automated testing due to key challenges: the lack of...

PiMRef: Detecting and Explaining Ever-Evolving Spear Phishing Emails with Knowledge Base Invariants

Phishing emails are a critical component of the cybercrime kill chain due to their wide reach and low cost. Their ever-evolving nature renders traditional rule-based and feature-engineered detectors ineffective in the ongoing arms race between attackers and defenders. The rise of large language...

Multi-Stage Prompt Inference Attacks on Enterprise LLM Systems

Large Language Models LLMs deployed in enterprise settings e.g., as Microsoft 365 Copilot face novel security challenges. One critical threat is prompt inference attacks: adversaries chain together seemingly benign prompts to gradually extract confidential data. In this paper, we present a...

Dippyis Insecure Direct Object Reference / Brute Force

Dippyis a popular website to chat with millions of proactive AI characters. The Dippy chat suffers from an insecure direct object reference vulnerability. Conversation histories for all users are stored on the server. However, Dippy's server does not distinguish the ownership or sharing status of...

ChatPlayground.ai Cross Site Scripting / Insecure Direct Object Reference

ChatPlayground.ai is a popular web application for comparing AI models. A cross site scripting vulnerability exists in the chat component. This can lead to JWT token theft and remote account hijacking. Additionally, the /api/chat-history endpoint exhibits weak access control allowing for insecure...

DP2Guard: a Lightweight and Byzantine-Robust Privacy-Preserving Federated Learning Scheme for Industrial IoT

Privacy-Preserving Federated Learning PPFL has emerged as a secure distributed Machine Learning ML paradigm that aggregates locally trained gradients without exposing raw data. To defend against model poisoning threats, several robustness-enhanced PPFL schemes have been proposed by integrating...

QSAF: a Novel Mitigation Framework for Cognitive Degradation in Agentic AI

We introduce Cognitive Degradation as a novel vulnerability class in agentic AI systems. Unlike traditional adversarial external threats such as prompt injection, these failures originate internally, arising from memory starvation, planner recursion, context flooding, and output suppression. Thes...

SVAgent: AI Agent for Hardware Security Verification Assertion

Verification using SystemVerilog assertions SVA is one of the most popular methods for detecting circuit design vulnerabilities. However, with the globalization of integrated circuit design and the continuous upgrading of security requirements, the SVA development model has exposed major...

Deepfiction AI Insecure Direct Object Reference

Deepfiction AI is an AI entertainment company with a mission to revolutionize personalized storytelling. Deepfiction AI provides a web application to create stories via chat and is susceptible to an insecure direct object reference vulnerability. An attacker can exploit this IDOR to chat with the...

ChatGPTUtil Cross Site Scripting

ChatGPTUtil is an AI-powered chatbot assistant, providing access to both ChatGPT and an AI image generator. A self cross site scripting vulnerability exists in the chat component. This can lead to cookie theft leading to remote account hijacking...

TelegAI Insecure Direct Object Reference

TelegAI, a web application for constructing and chatting with AI Characters, is vulnerable to insecure direct object reference in its chat component. An attacker can exploit this IDOR to tamper other users' conversation. Additionally, malicious contents and cross site scripting payloads can be...

Ai2 Insecure Direct Object Reference

Ai2 is a Seattle based non-profit AI research institute. Ai2 provides a playground web application to chat that is susceptible to an insecure direct object reference vulnerability. An attacker can exploit this IDOR to tamper other users' conversation...

AIBOX Cross Site Scripting

AIBOX is a web application for exploring AI consulting and trying out multiple LLMs. It allows users to chat with various LLMs. A reflected cross site scripting XSS vulnerability exists in the chat component, which could lead to JWT token theft and remote account hijacking...

TelegAI Cross Site Scripting

TelegAI, a web application for constructing and chatting with AI Characters, is vulnerable to persistent cross site scripting vulnerabilities in its chat component and character container component. An attacker can achieve arbitrary client-side script execution by crafting an AI Character with SV...

Chaindesk Cross Site Scripting

Chaindesk, a web application for constructing AI Agents, is vulnerable to a persistent cross site scripting vulnerability in its agent chat component. An attacker can achieve arbitrary client-side script execution by crafting an AI agent whose system prompt instructs the underlying Large Language...

PromptArmor: Simple yet Effective Prompt Injection Defenses

Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, causing it to perform an attacker-specified task rather than the intended task provided by the user. In this paper, we...

Adaptive Network Security Policies Via Belief Aggregation and Rollout

Evolving security vulnerabilities and shifting operational conditions require frequent updates to network security policies. These updates include adjustments to incident response procedures and modifications to access controls, among others. Reinforcement learning methods have been proposed for...

Clustered Federated Learning for Generalizable FDIA Detection in Smart Grids with Heterogeneous Data

False Data Injection Attacks FDIAs pose severe security risks to smart grids by manipulating measurement data collected from spatially distributed devices such as SCADA systems and PMUs. These measurements typically exhibit Non-Independent and Identically Distributed Non-IID characteristics acros...

Jamming-Resistant AAV Communications: a Multichannel-Aided Approach

Jamming cancellation is essential to reliable unmanned autonomous vehicle AAV communications in the presence of malicious jammers. In this paper, we develop a practical multichannel-aided jamming cancellation method to realize secure AAV communications. The proposed method is capable of...