Client-Side Zero-Shot LLM Inference for Comprehensive In-Browser URL Analysis

Malicious websites and phishing URLs pose an ever-increasing cybersecurity risk, with phishing attacks growing by 40% in a single year. Traditional detection approaches rely on machine learning classifiers or rule-based scanners operating in the cloud, but these face significant challenges in...

Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples

Adversarial detection protects models from adversarial attacks by refusing suspicious test samples. However, current detection methods often suffer from weak generalization: their effectiveness tends to degrade significantly when applied to adversarially trained models rather than naturally train...

Towards Trustworthy Federated Learning with Untrusted Participants

Resilience against malicious participants and data privacy are essential for trustworthy federated learning, yet achieving both with good utility typically requires the strong assumption of a trusted central server. This paper shows that a significantly weaker assumption suffices: each pair of...

Through the Stealth Lens: Rethinking Attacks and Defenses in RAG

Retrieval-augmented generation RAG systems are vulnerable to attacks that inject poisoned passages into the retrieved set, even at low corruption rates. We show that existing attacks are not designed to be stealthy, allowing reliable detection and mitigation. We formalize stealth using a...

FERRET: Private Deep Learning Faster and Better Than DPSGD

We revisit 1-bit gradient compression through the lens of mutual-information differential privacy MI-DP. Building on signSGD, we propose FERRET--Fast and Effective Restricted Release for Ethical Training--which transmits at most one sign bit per parameter group with Bernoulli masking. Theory: We...

TherMod Communication: Low Power or Hot Air?

The Kirchhoff-Law-Johnson-Noise KLJN secure key exchange scheme leverages statistical physics to enable secure communication with zero average power flow in a wired channel. While the original KLJN scheme requires significant power for operation, a recent wireless modification, TherMod, proposed ...

Attention Knows Whom to Trust: Attention-Based Trust Management for LLM Multi-Agent Systems

Large Language Model-based Multi-Agent Systems LLM-MAS have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable messages. This vulnerability stems from a fundamental gap: LLM agents treat all incoming messages equally without evaluating...

I2P 2.9.0

I2P is an anonymizing network, offering a simple layer that identity-sensitive applications can use to securely communicate. All data is wrapped with several layers of encryption, and the network is both distributed and dynamic, with no trusted parties. This is the source code release version...

A Review of Various Datasets for Machine Learning Algorithm-Based Intrusion Detection System: Advances and Challenges

IDS aims to protect computer networks from security threats by detecting, notifying, and taking appropriate action to prevent illegal access and protect confidential information. As the globe becomes increasingly dependent on technology and automated processes, ensuring secured systems,...

Poster: Libdebug, Build Your Own Debugger for a Better (Hello) World

Automated debugging, long pursued in a variety of fields from software engineering to cybersecurity, requires a framework that offers the building blocks for a programmable debugging workflow. However, existing debuggers are primarily tailored for human interaction, and those designed for...

LaSDVS : a Post-Quantum Secure Compact Strong-Designated Verifier Signature

Whitepaper called LaSDVS : A Post-Quantum Secure Compact Strong-Designated Verifier Signature...

Identifying Key Expert Actors in Cybercrime Forums Based on Their Technical Expertise

The advent of Big Data has made the collection and analysis of cyber threat intelligence challenging due to its volume, leading research to focus on identifying key threat actors; yet these studies have failed to consider the technical expertise of these actors. Expertise, especially towards...

Samsung S24 VC1 Decoder Out-Of-Bounds Memset

There are several calls to memset in the vc1 decoder on the Samsung S24, which can write out of bounds of a heap buffer. The length of the memsets in svc1expandrightapfrm are calculated based on length values that don't always correspond to the heap buffer length...

ATAG: AI-Agent Application Threat Assessment with Attack Graphs

Evaluating the security of multi-agent systems MASs powered by large language models LLMs is challenging, primarily because of the systems' complex internal dynamics and the evolving nature of LLM vulnerabilities. Traditional attack graph AG methods often lack the specific capabilities to model...

An Algorithmic Pipeline for GDPR-Compliant Healthcare Data Anonymisation: Moving toward Standardisation

High-quality real-world data RWD is essential for healthcare but must be transformed to comply with the General Data Protection Regulation GDPR. GDPRs broad definitions of quasi-identifiers QIDs and sensitive attributes SAs complicate implementation. We aim to standardise RWD anonymisation for GD...

ChainMarks: Securing DNN Watermark with Cryptographic Chain

With the widespread deployment of deep neural network DNN models, dynamic watermarking techniques are being used to protect the intellectual property of model owners. However, recent studies have shown that existing watermarking schemes are vulnerable to watermark removal and ambiguity attacks...

Vulnerability Management Chaining: an Integrated Framework for Efficient Cybersecurity Risk Prioritization

Cybersecurity teams face an overwhelming vulnerability crisis: with 25,000+ new CVEs disclosed annually, traditional CVSS-based prioritization requires addressing 60% of all vulnerabilities while correctly identifying only 20% of those actually exploited. We propose Vulnerability Management...

Combining Threat Intelligence with IoT Scanning to Predict Cyber Attack

While the Web has become a global platform for communication, malicious actors, including hackers and hacktivist groups, often disseminate ideological content and coordinate activities through the "Dark Web", an obscure counterpart of the conventional web. Presently, challenges such as informatio...

When Blockchain Meets Crawlers: Real-Time Market Analytics in Solana NFT Markets

In this paper, we design and implement a web crawler system based on the Solana blockchain for the automated collection and analysis of market data for popular non-fungible tokens NFTs on the chain. Firstly, the basic information and transaction data of popular NFTs on the Solana chain are...

Heterogeneous Secure Transmissions in IRS-Assisted NOMA Communications: CO-GNN Approach

Intelligent Reflecting Surfaces IRS enhance spectral efficiency by adjusting reflection phase shifts, while Non-Orthogonal Multiple Access NOMA increases system capacity. Consequently, IRS-assisted NOMA communications have garnered significant research interest. However, the passive nature of the...

Mind the Gap: a Practical Attack on GGUF Quantization

With the increasing size of frontier LLMs, post-training quantization has become the standard for memory-efficient deployment. Recent work has shown that basic rounding-based quantization schemes pose security risks, as they can be exploited to inject malicious behaviors into quantized models tha...

Youpot Worm Honeypot

Youpot listens on all TCP ports and connects to the attacker IP on the same port they connected to you on, proxying traffic back at them. This allows you to watch the attacker attack themselves. This project was presented at Confidence 2025...

Sylva: Tailoring Personalized Adversarial Defense in Pre-Trained Models Via Collaborative Fine-Tuning

Whitepaper called Sylva: Tailoring Personalized Adversarial Defense In Pre-Trained Models Via Collaborative Fine-Tuning...

Keyed Chaotic Dynamics for Privacy-Preserving Neural Inference

Neural network inference typically operates on raw input data, increasing the risk of exposure during preprocessing and inference. Moreover, neural architectures lack efficient built-in mechanisms for directly authenticating input data. This work introduces a novel encryption method for ensuring...

Secure and Private Federated Learning: Achieving Adversarial Resilience through Robust Aggregation

Federated Learning FL enables collaborative machine learning across decentralized data sources without sharing raw data. It offers a promising approach to privacy-preserving AI. However, FL remains vulnerable to adversarial threats from malicious participants, referred to as Byzantine clients, wh...

Decentralized COVID-19 Health System Leveraging Blockchain

With the development of the Internet, the amount of data generated by the medical industry each year has grown exponentially. The Electronic Health Record EHR manages the electronic data generated during the user's treatment process. Typically, an EHR data manager belongs to a medical institution...

Measuring Likelihood in Cybersecurity

In cybersecurity risk is commonly measured by impact and probability, the former is objectively measured based on the consequences from the use of technology to obtain business gains, or by achieving business objectives. The latter has been measured, in sectors such as financial or insurance, bas...

How Stealthy Is Stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real World

Deep learning systems, critical in domains like autonomous vehicles, are vulnerable to adversarial examples crafted inputs designed to mislead classifiers. This study investigates black-box adversarial attacks in computer vision. This is a realistic scenario, where attackers have query-only acces...

BadReward: Clean-Label Poisoning of Reward Models in Text-To-Image RLHF

Reinforcement Learning from Human Feedback RLHF is crucial for aligning text-to-image T2I models with human preferences. However, RLHF's feedback mechanism also opens new pathways for adversaries. This paper demonstrates the feasibility of hijacking T2I models by poisoning a small fraction of...

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents

Computer-Use Agents CUAs with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access user data, and execute arbitrary commands. While prior work has focused on browser-based agents and HTML-level attacks,...

Request-Baskets Server-Side Request Forgery

Request-Baskets versions up to 1.2.1 proof of concept server-side request forgery exploit...

Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack

Membership inference attack MIA has become one of the most widely used and effective methods for evaluating the privacy risks of machine learning models. These attacks aim to determine whether a specific sample is part of the model's training set by analyzing the model's output. While traditional...

Robust Anti-Backdoor Instruction Tuning in LVLMs

Large visual language models LVLMs have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually developed for single-modal visual or language models under...

Differentially Private Distribution Release of Gaussian Mixture Models Via KL-Divergence Minimization

Gaussian Mixture Models GMMs are widely used statistical models for representing multi-modal data distributions, with numerous applications in data mining, pattern recognition, data simulation, and machine learning. However, recent research has shown that releasing GMM parameters poses significan...

BitBypass: a New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage

The inherent risk of generating harmful and unsafe content by Large Language Models LLMs, has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and red-teaming were developed for ensuring the safety alignme...

Tarallo: Evading Behavioral Malware Detectors in the Problem Space

Machine learning algorithms can effectively classify malware through dynamic behavior but are susceptible to adversarial attacks. Existing attacks, however, often fail to find an effective solution in both the feature and problem spaces. This issue arises from not addressing the intrinsic...

Poster: FedBlockParadox -- a Framework for Simulating and Securing Decentralized Federated Learning

A significant body of research in decentralized federated learning focuses on combining the privacy-preserving properties of federated learning with the resilience and transparency offered by blockchain-based systems. While these approaches are promising, they often lack flexible tools to evaluat...

CyberGym: Evaluating AI Agents' Cybersecurity Capabilities with Real-World Vulnerabilities at Scale

Large language model LLM agents are becoming increasingly skilled at handling cybersecurity tasks autonomously. Thoroughly assessing their cybersecurity capabilities is critical and urgent, given the high stakes in this domain. However, existing benchmarks fall short, often failing to capture...

SAP GuiXT Scripting Issues

Multiple vulnerabilities have been discovered in SAP GuiXT scripting, which could allow an attacker to perform remote code execution, steal NTLM hashes, conduct client-side request forgery attacks, and launch denial of service DoS attacks. These vulnerabilities arise from insecure design principl...

Samsung S24 MP3 Decoder Out-Of-Bounds Read

There is an out-of-bounds read in the MP3 decoder in the Samsung S24. The function smp123djointstereov1 indexes into several tables for decoding, and does not check that the index is valid, allowing the tables to be read out of bounds. It may be possible to use this bug to bypass ASLR, as loading...

Samsung S24 VC1 Decoder Out-Of-Bounds Write

There is an out-of-bounds write to a heap buffer in the Samsung S24 VC1 decoder. The function svc1drrfrm can write outside of the allocated frame buffers in several locations due to incorrect calculations of buffer offsets...

Predictive-CSM: Lightweight Fragment Security for 6LoWPAN IoT Networks

Fragmentation is a routine part of communication in 6LoWPAN-based IoT networks, designed to accommodate small frame sizes on constrained wireless links. However, this process introduces a critical vulnerability fragments are typically stored and processed before their legitimacy is confirmed,...

ETDI: Mitigating Tool Squatting and Rug Pull Attacks in Model Context Protocol (MCP) by Using OAuth-Enhanced Tool Definitions and Policy-Based Access Control

The Model Context Protocol MCP plays a crucial role in extending the capabilities of Large Language Models LLMs by enabling integration with external tools and data sources. However, the standard MCP specification presents significant security vulnerabilities, notably Tool Poisoning and Rug Pull...

Policy As Code, Policy As Type

Policies are designed to distinguish between correct and incorrect actions; they are types. But badly typed actions may cause not compile errors, but financial and reputational harm We demonstrate how even the most complex ABAC policies can be expressed as types in dependently typed languages suc...

WordPress TI WooCommerce Wishlist 2.9.2 Arbitrary File Upload

WordPress TI WooCommerce Wishlist plugin versions 2.9.2 and below suffer from an arbitrary file upload vulnerability...

SMOTE-DP: Improving Privacy-Utility Tradeoff with Synthetic Data

Privacy-preserving data publication, including synthetic data sharing, often experiences trade-offs between privacy and utility. Synthetic data is generally more effective than data anonymization in balancing this trade-off, however, not without its own challenges. Synthetic data produced by...

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models

Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property IP of machine-learning-as-a-service MLaaS providers. Defending against such attacks is challenging, as it must balance efficiency, robustness, and utility...

Which Factors Make Code LLMs More Vulnerable to Backdoor Attacks? A Systematic Study

Code LLMs are increasingly employed in software development. However, studies have shown that they are vulnerable to backdoor attacks: when a trigger a specific input pattern appears in the input, the backdoor will be activated and cause the model to generate malicious outputs. Researchers have...

Peyara Remote Mouse 1.0.1 Unauthenticated Arbitrary File Upload

Peyara Remote Mouse version 1.0.1 suffers from an unauthenticated arbitrary file upload vulnerability...

Singularity Blockchain Key Management Via Non-Custodial Key Management

web3 wallets are key to managing user identity on blockchain. The main purpose of a web3 wallet application is to manage the private key for the user and provide an interface to interact with the blockchain. The key management scheme KMS used by the wallet to store and recover the private key can...