A Retrospective on DISPEED -- Leveraging Heterogeneity in a Drone Swarm for IDS Execution

Swarms of drones are gaining more and more autonomy and efficiency during their missions. However, security threats can disrupt their missions' progression. To overcome this problem, Network Intrusion Detection Systems NIDS are promising solutions to detect malicious behavior on network traffic...

UCD: Unlearning in LLMs Via Contrastive Decoding

Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models LLMs while preserving overall performance. We propose an inference-time unlearning algorithm that uses contrastive decoding, leveraging two auxiliary smaller models, one train...

TROJAN-GUARD: Hardware Trojans Detection Using GNN in RTL Designs

Chip manufacturing is a complex process, and to achieve a faster time to market, an increasing number of untrusted third-party tools and designs from around the world are being utilized. The use of these untrusted third party intellectual properties IPs and tools increases the risk of adversaries...

Alphabet Index Mapping: Jailbreaking LLMs through Semantic Dissimilarity

Large Language Models LLMs have demonstrated remarkable capabilities, yet their susceptibility to adversarial attacks, particularly jailbreaking, poses significant safety and ethical concerns. While numerous jailbreak methods exist, many suffer from computational expense, high token usage, or...

An Attack Method for Medical Insurance Claim Fraud Detection Based on Generative Adversarial Network

Insurance fraud detection represents a pivotal advancement in modern insurance service, providing intelligent and digitalized monitoring to enhance management and prevent fraud. It is crucial for ensuring the security and efficiency of insurance systems. Although AI and machine learning algorithm...

ArgHiTZ at ArchEHR-QA 2025: a Two-Step Divide and Conquer Approach to Patient Question Answering for Top Factuality

This work presents three different approaches to address the ArchEHR-QA 2025 Shared Task on automated patient question answering. We introduce an end-to-end prompt-based baseline and two two-step methods to divide the task, without utilizing any external knowledge. Both two step approaches first...

Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information

LLM-based Conversational AIs CAIs, also known as GenAI chatbots, like ChatGPT, are increasingly used across various domains, but they pose privacy risks, as users may disclose personal information during their conversations with CAIs. Recent research has demonstrated that LLM-based CAIs could be...

Universal Jailbreak Suffixes Are Strong Attention Hijackers

We study suffix-based jailbreaks$\unicodex2013$a powerful family of attacks against large language models LLMs that optimize adversarial suffixes to circumvent safety alignment. Focusing on the widely used foundational GCG attack Zou et al., 2023, we observe that suffixes vary in efficacy: some...

KEENHash: Hashing Programs into Function-Aware Embeddings for Large-Scale Binary Code Similarity Analysis

Binary code similarity analysis BCSA is a crucial research area in many fields such as cybersecurity. Specifically, function-level diffing tools are the most widely used in BCSA: they perform function matching one by one for evaluating the similarity between binary programs. However, such methods...

Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models

Large vision-language models LVLMs have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy risks if training images contain sensitive information. Therefore, it is important to detect whether an image is used t...

When Forgetting Triggers Backdoors: a Clean Unlearning Attack

Machine unlearning has emerged as a key component in ensuring Right to be Forgotten, enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set clean unlearning, it can be exploited for stealthy attacks that...

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks Via Security-Aware Prompt Compression

Large language models LLMs have achieved widespread adoption across numerous applications. However, many LLMs are vulnerable to malicious attacks even after safety alignment. These attacks typically bypass LLMs' safety guardrails by wrapping the original malicious instructions inside adversarial...

Watermarking Quantum Neural Networks Based on Sample Grouped and Paired Training

Quantum neural networks QNNs leverage quantum computing to create powerful and efficient artificial intelligence models capable of solving complex problems significantly faster than traditional computers. With the fast development of quantum hardware technology, such as superconducting qubits,...

Generalization under Byzantine and Poisoning Attacks: Tight Stability Bounds in Robust Distributed Learning

Whitepaper called Generalization Under Byzantine and Poisoning Attacks: Tight Stability Bounds In Robust Distributed Learning...

Mechanistic Interpretability in the Presence of Architectural Obfuscation

Architectural obfuscation - e.g., permuting hidden-state tensors, linearly transforming embedding tables, or remapping tokens - has recently gained traction as a lightweight substitute for heavyweight cryptography in privacy-preserving large-language-model LLM inference. While recent work has sho...

Secure User-Friendly Blockchain Modular Wallet Design Using Android and OP-TEE

Emerging crypto economies still hemorrhage digital assets because legacy wallets leak private keys at almost every layer of the software stack, from user-space libraries to kernel memory dumps. This paper solves that twin crisis of security and interoperability by re-imagining key management as a...

Pushing the Limits of Safety: a Technical Report on the ATLAS Challenge 2025

Multimodal Large Language Models MLLMs have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and improve their safety, we organized the Adversarial Testing...

Federated Learning-Based Data Collaboration Method for Enhancing Edge Cloud AI System Security Using Large Language Models

With the widespread application of edge computing and cloud systems in AI-driven applications, how to maintain efficient performance while ensuring data privacy has become an urgent security issue. This paper proposes a federated learning-based data collaboration method to improve the security of...

FAA Framework: a Large Language Model-Based Approach for Credit Card Fraud Investigations

The continuous growth of the e-commerce industry attracts fraudsters who exploit stolen credit card details. Companies often investigate suspicious transactions in order to retain customer trust and address gaps in their fraud detection systems. However, analysts are overwhelmed with an enormous...

SoK: the Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation

Large language models LLMs are sophisticated artificial intelligence systems that enable machines to generate human-like text with remarkable precision. While LLMs offer significant technological progress, their development using vast amounts of user data scraped from the web and collected from...

SoK: Automated Vulnerability Repair: Methods, Tools, and Assessments

The increasing complexity of software has led to the steady growth of vulnerabilities. Vulnerability repair investigates how to fix software vulnerabilities. Manual vulnerability repair is labor-intensive and time-consuming because it relies on human experts, highlighting the importance of...

Organizational Adaptation to Generative AI in Cybersecurity: a Systematic Review

Cybersecurity organizations are adapting to GenAI integration through modified frameworks and hybrid operational processes, with success influenced by existing security maturity, regulatory requirements, and investments in human capital and infrastructure. This qualitative research employs...

Leakage-Resilient Extractors against Number-On-Forehead Protocols

Given a sequence of $N$ independent sources $\mathbfX1,\mathbfX2,\dots,\mathbfXN\sim\0,1^n$, how many of them must be good i.e., contain some min-entropy in order to extract a uniformly random string? This question was first raised by Chattopadhyay, Goodman, Goyal and Li STOC '20, motivated by...

Privacy-Preserving Federated Learning against Malicious Clients Based on Verifiable Functional Encryption

Federated learning is a promising distributed learning paradigm that enables collaborative model training without exposing local client data, thereby protect data privacy. However, it also brings new threats and challenges. The advancement of model inversion attacks has rendered the plaintext...

VulStamp: Vulnerability Assessment Using Large Language Model

Although modern vulnerability detection tools enable developers to efficiently identify numerous security flaws, indiscriminate remediation efforts often lead to superfluous development expenses. This is particularly true given that a substantial portion of detected vulnerabilities either possess...

Bidirectional Biometric Authentication Using Transciphering and (T)FHE

Biometric authentication systems pose privacy risks, as leaked templates such as iris or fingerprints can lead to security breaches. Fully Homomorphic Encryption FHE enables secure encrypted evaluation, but its deployment is hindered by large ciphertexts, high key overhead, and limited trust...

Optimizing Resource Allocation and Energy Efficiency in Federated Fog Computing for IoT

Address Resolution Protocol ARP spoofing attacks severely threaten Internet of Things IoT networks by allowing attackers to intercept, modify, or block communications. Traditional detection methods are insufficient due to high false positives and poor adaptability. This research proposes a...

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models Via Trigger Inversion and Activation Tuning

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that persist through downstream tasks, enabling malicious control ...

InfoFlood: Jailbreaking Large Language Models with Information Overload

Large Language Models LLMs have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by adversarial techniques known as "jailbreak" attacks. Existing...

Secure API-Driven Research Automation to Accelerate Scientific Discovery

The Secure Scientific Service Mesh S3M provides API-driven infrastructure to accelerate scientific discovery through automated research workflows. By integrating near real-time streaming capabilities, intelligent workflow orchestration, and fine-grained authorization within a service mesh...

Exploring the Secondary Risks of Large Language Models

Ensuring the safety and alignment of Large Language Models is a significant challenge with their growing integration into critical applications and societal functions. While prior research has primarily focused on jailbreak attacks, less attention has been given to non-adversarial failures that...

An Efficient Hardware Implementation of Elliptic Curve Point Multiplication over $GF(2^M)$ on FPGA

Elliptic Curve Cryptography ECC is widely accepted for ensuring secure data exchange between resource-limited IoT devices. The National Institute of Standards and Technology NIST recommended implementation, such as B-163, is particularly well-suited for Internet of Things IoT applications. Here,...

Prohibited Items Segmentation Via Occlusion-Aware Bilayer Modeling

Instance segmentation of prohibited items in security X-ray images is a critical yet challenging task. This is mainly caused by the significant appearance gap between prohibited items in X-ray images and natural objects, as well as the severe overlapping among objects in X-ray images. To address...

LLM Embedding-Based Attribution (LEA): Quantifying Source Contributions to Generative Model'S Response for Vulnerability Analysis

Security vulnerabilities are rapidly increasing in frequency and complexity, creating a shifting threat landscape that challenges cybersecurity defenses. Large Language Models LLMs have been widely adopted for cybersecurity threat analysis. When querying LLMs, dealing with new, unseen...

Embedding Trust at Scale: Physics-Aware Neural Watermarking for Secure and Verifiable Data Pipelines

We present a robust neural watermarking framework for scientific data integrity, targeting high-dimensional fields common in climate modeling and fluid simulations. Using a convolutional autoencoder, binary messages are invisibly embedded into structured data such as temperature, vorticity, and...

PuDHammer: Experimental Analysis of Read Disturbance Effects of Processing-Using-DRAM in Real DRAM Chips

Processing-using-DRAM PuD is a promising paradigm for alleviating the data movement bottleneck using DRAM's massive internal parallelism and bandwidth to execute very wide operations. Performing a PuD operation involves activating multiple DRAM rows in quick succession or simultaneously, i.e.,...

Shelter Soul: Bridging Shelters and Adopters through Technology

Pet adoption processes often face inefficiencies, including limited accessibility, lack of real-time information, and mismatched expectations between shelters and adopters. To address these challenges, this study presents Shelter Soul, a technology-based solution designed to streamline pet adopti...

Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates

Whitepaper called Differentially Private Bilevel Optimization: Efficient Algorithms With Near-Optimal Rates...

CnC-PRAC: Coalesce, Not Cache, Per Row Activation Counts for an Efficient In-DRAM Rowhammer Mitigation

JEDEC has introduced the Per Row Activation Counting PRAC framework for DDR5 and future DRAMs to enable precise counting of DRAM row activations using per-row activation counts. While recent PRAC implementations enable holistic mitigation of Rowhammer attacks, they impose slowdowns of up to 10% d...

Toward a Lightweight, Scalable, and Parallel Secure Encryption Engine

The exponential growth of Internet of Things IoT applications has intensified the demand for efficient, high-throughput, and energy-efficient data processing at the edge. Conventional CPU-centric encryption methods suffer from performance bottlenecks and excessive data movement, especially in...

Autonomous 3D Moving Target Encirclement and Interception with Range Measurement

Commercial UAVs are an emerging security threat as they are capable of carrying hazardous payloads or disrupting air traffic. To counter UAVs, we introduce an autonomous 3D target encirclement and interception strategy. Unlike traditional ground-guided systems, this strategy employs autonomous...

An Advanced Reliability Reserve Incentivizes Flexibility Investments While Safeguarding the Electricity Market

To ensure security of supply in the power sector, many countries are already using or discussing the introduction of capacity mechanisms. Two main types of such mechanisms include capacity markets and capacity reserves. Simultaneously, the expansion of variable renewable energy sources increases...

Exploiting Efficiency Vulnerabilities in Dynamic Deep Learning Systems

The growing deployment of deep learning models in real-world environments has intensified the need for efficient inference under strict latency and resource constraints. To meet these demands, dynamic deep learning systems DDLSs have emerged, offering input-adaptive computation to optimize runtim...

Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers

Although Foundation Models FMs, such as GPT-4, are increasingly used in domains like finance and software engineering, reliance on textual interfaces limits these models' real-world interaction. To address this, FM providers introduced tool calling-triggering a proliferation of frameworks with...

The Redundancy of Full Nodes in Bitcoin: a Network-Theoretic Demonstration of Miner-Centric Propagation Topologies

This paper formally examines the network structure of Bitcoin CORE BTC and Bitcoin Satoshi Vision BSV using complex graph theory to demonstrate that home-hosted full nodes are incapable of participating in or influencing the propagation topology. Leveraging established models such as scale-free...

LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Data

Large language models LLMs can be trained or fine-tuned on data obtained without the owner's consent. Verifying whether a specific LLM was trained on particular data instances or an entire dataset is extremely challenging. Dataset watermarking addresses this by embedding identifiable modification...

Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and Explainability

Phishing attacks remain one of the most prevalent and persistent cybersecurity threat with attackers continuously evolving and intensifying tactics to evade the general detection system. Despite significant advances in artificial intelligence and machine learning, faithfully reproducing the...

Foundation of Affective Computing and Interaction

This book provides a comprehensive exploration of affective computing and human-computer interaction technologies. It begins with the historical development and basic concepts of human-computer interaction, delving into the technical frameworks and practical applications of emotional computing,...

Unlearning-Enhanced Website Fingerprinting Attack: against Backdoor Poisoning in Anonymous Networks

Website Fingerprinting WF is an effective tool for regulating and governing the dark web. However, its performance can be significantly degraded by backdoor poisoning attacks in practical deployments. This paper aims to address the problem of hidden backdoor poisoning attacks faced by Website...

One-shot Face Sketch Synthesis in the Wild via Generative Diffusion Prior and Instruction Tuning

Face sketch synthesis is a technique aimed at converting face photos into sketches. Existing face sketch synthesis research mainly relies on training with numerous photo-sketch sample pairs from existing datasets. However, these large-scale discriminative learning methods will have to face proble...