Probing the Robustness of Large Language Models Safety to Latent Perturbations

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We argue that this stems from the shallow nature of existing...

AndroIDS : Android-Based Intrusion Detection System Using Federated Learning

The exponential growth of android-based mobile IoT systems has significantly increased the susceptibility of devices to cyberattacks, particularly in smart homes, UAVs, and other connected mobile environments. This article presents a federated learning-based intrusion detection framework called...

Black-Box Privacy Attacks on Shared Representations in Multitask Learning

Multitask learning MTL has emerged as a powerful paradigm that leverages similarities among multiple learning tasks, each with insufficient samples to train a standalone model, to solve them simultaneously while minimizing data sharing across users and organizations. MTL typically accomplishes th...

Advantech WISE 4060LAN / IoT Gateway Packet Injection

Remote attackers can execute Modbus commands to WISE-4060/LAN module and manipulate the DO channels. This could lead to unauthorized control of connected devices, such as turning systems on or off, causing disruptions or unsafe conditions. In industrial settings, the DO channels might control...

SAFER-D: a Self-Adaptive Security Framework for Distributed Computing Architectures

The rise of the Internet of Things and Cyber-Physical Systems has introduced new challenges on ensuring secure and robust communication. The growing number of connected devices increases network complexity, leading to higher latency and traffic. Distributed computing architectures DCAs have gaine...

Watermarking Autoregressive Image Generation

Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has attempted to watermark their outputs at the token level. In thi...

SecureFed: a Two-Phase Framework for Detecting Malicious Clients in Federated Learning

Federated Learning FL protects data privacy while providing a decentralized method for training models. However, because of the distributed schema, it is susceptible to adversarial clients that could alter results or sabotage model performance. This study presents SecureFed, a two-phase FL...

Exploring Traffic Simulation and Cybersecurity Strategies Using Large Language Models

Intelligent Transportation Systems ITS are increasingly vulnerable to sophisticated cyberattacks due to their complex, interconnected nature. Ensuring the cybersecurity of these systems is paramount to maintaining road safety and minimizing traffic disruptions. This study presents a novel...

A Sea of Cyber Threats: Maritime Cybersecurity from the Perspective of Mariners

Maritime systems, including ships and ports, are critical components of global infrastructure, essential for transporting over 80% of the world's goods and supporting internet connectivity. However, these systems face growing cybersecurity threats, as shown by recent attacks disrupting Maersk, on...

Bias Variation Compensation in Perimeter-Gated SPAD TRNGs

Random number generators that utilize arrays of entropy source elements suffer from bias variation BV. Despite the availability of efficient debiasing algorithms, optimized implementations of hardware friendly options depend on the bit bias in the raw bit streams and cannot accommodate a wide BV...

Unsourced Adversarial CAPTCHA: a Bi-Phase Adversarial CAPTCHA Framework

With the rapid advancements in deep learning, traditional CAPTCHA schemes are increasingly vulnerable to automated attacks powered by deep neural networks DNNs. Existing adversarial attack methods often rely on original image characteristics, resulting in distortions that hinder human...

Sudoku: Decomposing DRAM Address Mapping into Component Functions

Decomposing DRAM address mappings into component-level functions is critical for understanding memory behavior and enabling precise RowHammer attacks, yet existing reverse-engineering methods fall short. We introduce novel timing-based techniques leveraging DRAM refresh intervals and consecutive...

Graph Neural Networks for Jamming Source Localization

Graph-based learning provides a powerful framework for modeling complex relational structures; however, its application within the domain of wireless security remains significantly underexplored. In this work, we introduce the first application of graph-based learning for jamming source...

Rubber Mallet: a Study of High Frequency Localized Bit Flips and Their Impact on Security

The increasing density of modern DRAM has heightened its vulnerability to Rowhammer attacks, which induce bit flips by repeatedly accessing specific memory rows. This paper presents an analysis of bit flip patterns generated by advanced Rowhammer techniques that bypass existing hardware defenses...

Efficient Malware Detection with Optimized Learning on High-Dimensional Features

Malware detection using machine learning requires feature extraction from binary files, as models cannot process raw binaries directly. A common approach involves using LIEF for raw feature extraction and the EMBER vectorizer to generate 2381-dimensional feature vectors. However, the high...

Tracking GPTs Third Party Service: Automation, Analysis, and Insights

ChatGPT has quickly advanced from simple natural language processing to tackling more sophisticated and specialized tasks. Drawing inspiration from the success of mobile app ecosystems, OpenAI allows developers to create applications that interact with third-party services, known as GPTs. GPTs ca...

Context Manipulation Attacks : Web Agents Are Susceptible to Corrupted Memory

Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, information retrieval, and content discovery. Due to the stateless nature of large language models LLMs, these agents...

A Nested Watermark for Large Language Models

The rapid advancement of large language models LLMs has raised concerns regarding their potential misuse, particularly in generating fake news and misinformation. To address these risks, watermarking techniques for autoregressive language models have emerged as a promising means for detecting...

Trustworthy Artificial Intelligence for Cyber Threat Analysis

Artificial Intelligence brings innovations into the society. However, bias and unethical exist in many algorithms that make the applications less trustworthy. Threats hunting algorithms based on machine learning have shown great advantage over classical methods. Reinforcement learning models are...

Clam AntiVirus Toolkit 1.4.3

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...

On the Performance of Cyber-Biomedical Features for Intrusion Detection in Healthcare 5.0

Healthcare 5.0 integrates Artificial Intelligence AI, the Internet of Things IoT, real-time monitoring, and human-centered design toward personalized medicine and predictive diagnostics. However, the increasing reliance on interconnected medical technologies exposes them to cyber threats...

Beyond the Scope: Security Testing of Permission Management in Team Workspace

Nowadays team workspaces are widely adopted for multi-user collaboration and digital resource management. To further broaden real-world applications, mainstream team workspaces platforms, such as Google Workspace and Microsoft OneDrive, allow third-party applications referred to as add-ons to be...

FARFETCH'D: a Side-Channel Analysis Framework for Privacy Applications on Confidential Virtual Machines

Confidential virtual machines CVMs based on trusted execution environments TEEs enable new privacy-preserving solutions. Yet, they leave side-channel leakage outside their threat model, shifting the responsibility of mitigating such attacks to developers. However, mitigations are either not gener...

Tech-ASan: Two-Stage Check for Address Sanitizer

Address Sanitizer ASan is a sharp weapon for detecting memory safety violations, including temporal and spatial errors hidden in C/C++ programs during execution. However, ASan incurs significant runtime overhead, which limits its efficiency in testing large software. The overhead mainly comes fro...

ETrace:Event-Driven Vulnerability Detection in Smart Contracts Via LLM-Based Trace Analysis

With the advance application of blockchain technology in various fields, ensuring the security and stability of smart contracts has emerged as a critical challenge. Current security analysis methodologies in vulnerability detection can be categorized into static analysis and dynamic analysis...

Multi-Use LLM Watermarking and the False Detection Problem

Digital watermarking is a promising solution for mitigating some of the risks arising from the misuse of automatically generated text. These approaches either embed non-specific watermarks to allow for the detection of any text generated by a particular sampler, or embed specific keys that allow...

Dynamic Risk Assessments for Offensive Cybersecurity Agents

Foundation models are increasingly becoming better autonomous programmers, raising the prospect that they could also automate dangerous offensive cyber-operations. Current frontier model audits probe the cybersecurity risks of such agents, but most fail to account for the degrees of freedom...

Version-Level Third-Party Library Detection in Android Applications Via Class Structural Similarity

Android applications apps integrate reusable and well-tested third-party libraries TPLs to enhance functionality and shorten development cycles. However, recent research reveals that TPLs have become the largest attack surface for Android apps, where the use of insecure TPLs can compromise both...

KGMark: a Diffusion Watermark for Knowledge Graphs

Knowledge graphs KGs are ubiquitous in numerous real-world applications, and watermarking facilitates protecting intellectual property and preventing potential harm from AI-generated content. Existing watermarking methods mainly focus on static plain text or image data, while they can hardly be...

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems

The rapid advancement of Large Language Models LLMs has led to the emergence of Multi-Agent Systems MAS to perform complex tasks through collaboration. However, the intricate nature of MAS, including their architecture and agent interactions, raises significant concerns regarding intellectual...

On Key Exchange Protocol Based on Two-Side Multiplication Action

We present a cryptanalysis of a key exchange protocol based on the digital semiring. For this purpose, we find the maximal solution of a linear system over such semiring, and use the properties of circulant matrix to demonstrate that the protocol is vulnerable. Specifically, we provide an efficie...

LLM Jailbreak Oracle

As large language models LLMs become increasingly deployed in safety-critical applications, the lack of systematic methods to assess their vulnerability to jailbreak attacks presents a critical security gap. We introduce the jailbreak oracle problem: given a model, prompt, and decoding strategy,...

PolyGuard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset

Whitepaper called PolyGuard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset...

Falco 0.41.2

Sysdig Falco is a behavioral activity monitoring agent that is open source and comes with native support for containers. Falco lets you define highly granular rules to check for activities involving file and network activity, process execution, IPC, and much more, using a flexible syntax. Falco...

Proposal for Improving Google A2A Protocol: Safeguarding Sensitive Data in Multi-Agent Systems

A2A, a protocol for AI agent communication, offers a robust foundation for secure AI agent communication. However, it has several critical issues in handling sensitive data, such as payment details, identification documents, and personal information. This paper reviews the existing protocol,...

Think Twice Before Adaptation: Improving Adaptability of DeepFake Detection Via Online Test-Time Adaptation

Whitepaper called Think Twice Before Adaptation: Improving Adaptability Of DeepFake Detection Via Online Test-Time Adaptation...

Technical Options for Flexible Hardware-Enabled Guarantees

Frontier AI models pose increasing risks to public safety and international security, creating a pressing need for AI developers to provide credible guarantees about their development activities without compromising proprietary information. We propose Flexible Hardware-Enabled Guarantees flexHEG,...

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

As Large Language Models LLMs are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals...

Safety Features for a Centralised AGI Project

Recent AI progress has outpaced expectations, with some experts now predicting AI that matches or exceeds human capabilities in all cognitive areas AGI could emerge this decade, potentially posing grave national and global security threats. AI development is currently occurring primarily in the...

Theoretically Unmasking Inference Attacks against LDP-Protected Clients in Federated Vision Models

Federated Learning enables collaborative learning among clients via a coordinating server while avoiding direct data sharing, offering a perceived solution to preserve privacy. However, recent studies on Membership Inference Attacks MIAs have challenged this notion, showing high success rates...

Miliaris Amigdala 2.2.6 Cross Site Scripting

Miliaris Amigdala version 2.2.6 suffers from multiple reflective cross site scripting vulnerabilities. Please note this entry aggregates three separate advisories...

Mitigating Data Poisoning Attacks to Local Differential Privacy

The distributed nature of local differential privacy LDP invites data poisoning attacks and poses unforeseen threats to the underlying LDP-supported applications. In this paper, we propose a comprehensive mitigation framework for popular frequency estimation, which contains a suite of novel...

Specification and Evaluation of Multi-Agent LLM Systems -- Prototype and Cybersecurity Applications

Recent advancements in LLMs indicate potential for novel applications, e.g., through reasoning capabilities in the latest OpenAI and DeepSeek models. For applying these models in specific domains beyond text generation, LLM-based multi-agent approaches can be utilized that solve complex tasks by...

Can We Infer Confidential Properties of Training Data from LLMs?

Large language models LLMs are increasingly fine-tuned on domain-specific datasets to support applications in fields such as healthcare, finance, and law. These fine-tuning datasets often have sensitive and confidential dataset-level properties -- such as patient demographics or disease prevalenc...

Optimal Piecewise-Based Mechanism for Collecting Bounded Numerical Data under Local Differential Privacy

Numerical data with bounded domains is a common data type in personal devices, such as wearable sensors. While the collection of such data is essential for third-party platforms, it raises significant privacy concerns. Local differential privacy LDP has been shown as a framework providing provabl...

Locally Differentially Private Frequency Estimation Via Joint Randomized Response

Local Differential Privacy LDP has been widely recognized as a powerful tool for providing a strong theoretical guarantee of data privacy to data contributors against an untrusted data collector. Under a typical LDP scheme, each data contributor independently randomly perturbs their data before...

I Know What You Said: Unveiling Hardware Cache Side-Channels in Local Large Language Model Inference

Large Language Models LLMs that can be deployed locally have recently gained popularity for privacy-sensitive tasks, with companies such as Meta, Google, and Intel playing significant roles in their development. However, the security of local LLMs through the lens of hardware cache side-channels...

The Safety Reminder: a Soft Prompt to Reactivate Delayed Safety Awareness in Vision-Language Models

As Vision-Language Models VLMs demonstrate increasing capabilities across real-world applications such as code generation and chatbot assistance, ensuring their safety has become paramount. Unlike traditional Large Language Models LLMs, VLMs face unique vulnerabilities due to their multimodal...

Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors

Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm in the immediate prompt and do not reason about long-rang...

Parallel Repetition for Post-Quantum Arguments

In this work, we show that parallel repetition of public-coin interactive arguments reduces the soundness error at an exponential rate even in the post-quantum setting. Moreover, we generalize this result to hold for threshold verifiers, where the parallel repeated verifier accepts if and only if...