TokenBreak: Bypassing Text Classification Models through Token Manipulation

Natural Language Processing NLP models are used for text-related tasks such as classification and generation. To complete these tasks, input data is first tokenized from human-readable text into a format the model can understand, enabling it to make inferences and understand context. Text...

SHIELD: Secure Hypernetworks for Incremental Expansion Learning Defense

Traditional deep neural networks suffer from several limitations, including catastrophic forgetting. When models are adapted to new datasets, they tend to quickly forget previously learned knowledge. Another significant issue is the lack of robustness to even small perturbations in the input data...

CAPAA: Classifier-Agnostic Projector-Based Adversarial Attack

Projector-based adversarial attack aims to project carefully designed light patterns i.e., adversarial projections onto scenes to deceive deep image classifiers. It has potential applications in privacy protection and the development of more robust classifiers. However, existing approaches...

IF-GUIDE: Influence Function-Guided Detoxification of LLMs

We study how training data contributes to the emergence of toxic behaviors in large-language models. Most prior work on reducing model toxicity adopts $reactive$ approaches, such as fine-tuning pre-trained and potentially toxic models to align them with human values. In contrast, we propose a...

SoK: Data Reconstruction Attacks against Machine Learning Models: Definition, Metrics, and Benchmark

Data reconstruction attacks, which aim to recover the training dataset of a target model with limited access, have gained increasing attention in recent years. However, there is currently no consensus on a formal definition of data reconstruction attacks or appropriate evaluation metrics for...

GradEscape: a Gradient-Based Evader against AI-Generated Text Detectors

In this paper, we introduce GradEscape, the first gradient-based evader designed to attack AI-generated text AIGT detectors. GradEscape overcomes the undifferentiable computation problem, caused by the discrete nature of text, by introducing a novel approach to construct weighted embeddings for t...

Evaluating Explainable AI for Deep Learning-Based Network Intrusion Detection System Alert Classification

A Network Intrusion Detection System NIDS monitors networks for cyber attacks and other unwanted activities. However, NIDS solutions often generate an overwhelming number of alerts daily, making it challenging for analysts to prioritize high-priority threats. While deep learning models promise to...

Explainable AI for Enhancing IDS against Advanced Persistent Kill Chain

Advanced Persistent Threats APTs represent a sophisticated and persistent cy-bersecurity challenge, characterized by stealthy, multi-phase, and targeted attacks aimed at compromising information systems over an extended period. Develop-ing an effective Intrusion Detection System IDS capable of...

Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models

Large Language Models LLMs memorize, and thus, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information PII, which should not be stored and, consequently, not leaked. In this paper, we introduce Private Memorization Editing PME, an approach for preventing private...

Pixel-Sensitive and Robust Steganography Based on Polar Codes

Steganography is an information hiding technique for covert communication. The core issue in steganography design is the rate-distortion coding problem. Polar codes, which have been proven to achieve the rate-distortion bound for any binary symmetric source, are utilized to design a steganographi...

SCGAgent: Recreating the Benefits of Reasoning Models for Secure Code Generation with Agentic Workflows

Large language models LLMs have seen widespread success in code generation tasks for different scenarios, both everyday and professional. However current LLMs, despite producing functional code, do not prioritize security and may generate code with exploitable vulnerabilities. In this work, we...

STAMP Your Content: Proving Dataset Membership Via Watermarked Rephrasings

Given how large parts of publicly available text are crawled to pretrain large language models LLMs, data creators increasingly worry about the inclusion of their proprietary data for model training without attribution or licensing. Their concerns are also shared by benchmark curators whose...

D2R: Dual Regularization Loss with Collaborative Adversarial Generation for Model Robustness

The robustness of Deep Neural Network models is crucial for defending models against adversarial attacks. Recent defense methods have employed collaborative learning frameworks to enhance model robustness. Two key limitations of existing methods are i insufficient guidance of the target model via...

Insecurity through Obscurity: Veiled Vulnerabilities in Closed-Source Contracts

Most blockchains cannot hide the binary code of programs i.e., smart contracts running on them. To conceal proprietary business logic and to potentially deter attacks, many smart contracts are closed-source and employ layers of obfuscation. However, we demonstrate that such obfuscation can obscur...

Mind the Web: the Security of Web Use Agents

Web-use agents are rapidly being deployed to automate complex web tasks, operating with extensive browser capabilities including multi-tab navigation, DOM manipulation, JavaScript execution and authenticated session access. However, these powerful capabilities create a critical and previously...

MARVEL: Multi-Agent RTL Vulnerability Extraction Using Large Language Models

Hardware security verification is a challenging and time-consuming task. For this purpose, design engineers may utilize tools such as formal verification, linters, and functional simulation tests, coupled with analysis and a deep understanding of the hardware design being inspected. Large Languag...

Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures

Large language models LLMs are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly answering harmless-looking inputs can be dangerous and cause...

Exploiting Inaccurate Branch History in Side-Channel Attacks

Modern out-of-order CPUs heavily rely on speculative execution for performance optimization, with branch prediction serving as a cornerstone to minimize stalls and maximize efficiency. Whenever shared branch prediction resources lack proper isolation and sanitization methods, they may originate...

Enhancing Watermarking Quality for LLMs Via Contextual Generation States Awareness

Recent advancements in watermarking techniques have enabled the embedding of secret messages into AI-generated text AIGT, serving as an important mechanism for AIGT detection. Existing methods typically interfere with the generation processes of large language models LLMs to embed signals within...

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

The remarkable success of Large Language Models LLMs has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both...

NanoZone: Scalable, Efficient, and Secure Memory Protection for Arm CCA

Arm Confidential Computing Architecture CCA currently isolates at the granularity of an entire Confidential Virtual Machine CVM, leaving intra-VM bugs such as Heartbleed unmitigated. The state-of-the-art narrows this to the process level, yet still cannot stop attacks that pivot within the same...

Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models

Differential Privacy DP is a widely adopted technique, valued for its effectiveness in protecting the privacy of task-specific datasets, making it a critical tool for large language models. However, its effectiveness in Multimodal Large Language Models MLLMs remains uncertain. Applying Differenti...

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation

Vision Language Models VLMs have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality triggers, leaving the crucial cross-modal fusion nature of...

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint

As LLMs are increasingly deployed in real-world applications, ensuring their ability to refuse malicious prompts, especially jailbreak attacks, is essential for safe and reliable use. Recently, activation steering has emerged as an effective approach for enhancing LLM safety by adding a refusal...

From Static to Adaptive Defense: Federated Multi-Agent Deep Reinforcement Learning-Driven Moving Target Defense against DoS Attacks in UAV Swarm Networks

The proliferation of unmanned aerial vehicle UAV swarms has enabled a wide range of mission-critical applications, but also exposes UAV networks to severe Denial-of-Service DoS threats due to their open wireless environment, dynamic topology, and resource constraints. Traditional static or...

Efficient RL-Based Cache Vulnerability Exploration by Penalizing Useless Agent Actions

Cache-timing attacks exploit microarchitectural characteristics to leak sensitive data, posing a severe threat to modern systems. Despite its severity, analyzing the vulnerability of a given cache structure against cache-timing attacks is challenging. To this end, a method based on Reinforcement...

HauntAttack: When Attack Follows Reasoning As a Shadow

Emerging Large Reasoning Models LRMs consistently excel in mathematical and reasoning tasks, showcasing exceptional capabilities. However, the enhancement of reasoning abilities and the exposure of their internal reasoning processes introduce new safety vulnerabilities. One intriguing concern is:...

ModelForge: Using GenAI to Improve the Development of Security Protocols

Formal methods can be used for verifying security protocols, but their adoption can be hindered by the complexity of translating natural language protocol specifications into formal representations. In this paper, we introduce ModelForge, a novel tool that automates the translation of protocol...

Enhanced Consistency Bi-Directional GAN(CBiGAN) for Malware Anomaly Detection

Static analysis, a cornerstone technique in cybersecurity, offers a noninvasive method for detecting malware by analyzing dormant software without executing potentially harmful code. However, traditional static analysis often relies on biased or outdated datasets, leading to gaps in detection...

JavelinGuard: Low-Cost Transformer Architectures for LLM Security

We present JavelinGuard, a suite of low-cost, high-performance model architectures designed for detecting malicious intent in Large Language Model LLM interactions, optimized specifically for production deployment. Recent advances in transformer architectures, including compact BERTDevlin et al...

A Simulation-Based Evaluation Framework for Inter-VM RowHammer Mitigation Techniques

Inter-VM RowHammer is an attack that induces a bitflip beyond the boundaries of virtual machines VMs to compromise a VM from another, and some software-based techniques have been proposed to mitigate this attack. Evaluating these mitigation techniques requires to confirm that they actually mitiga...

An Ultra-Sub-Wavelength Microwave Polarization Switch Implemented with Directed Surface Acoustic Waves in a Magnonic Crystal

The ability to switch the polarization of a transmitted electromagnetic wave from vertical to horizontal, or vice versa, is of great technological interest because of its many applications in long distance communication. Binary bits can be encoded in two orthogonal polarizations and transmitted...

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment

Safely aligning large language models LLMs often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods frequently rely on complex iterative prompting or auxiliary models. To address...

Shuffling Cards When You Are of Very Little Brain: Low Memory Generation of Permutations

How can we generate a permutation of the numbers $1$ through $n$ so that it is hard to guess the next element given the history so far? The twist is that the generator of the permutation the "Dealer" has limited memory, while the "Guesser" has unlimited memory. With unbounded memory actually $n$...

Fuse and Federate: Enhancing EV Charging Station Security with Multimodal Fusion and Federated Learning

The rapid global adoption of electric vehicles EVs has established electric vehicle supply equipment EVSE as a critical component of smart grid infrastructure. While essential for ensuring reliable energy delivery and accessibility, EVSE systems face significant cybersecurity challenges, includin...

SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large Embedding

Federated recommender system FedRec has emerged as a solution to protect user data through collaborative training techniques. A typical FedRec involves transmitting the full model and entire weight updates between edge devices and the server, causing significant burdens to devices with limited...

Ai-Driven Vulnerability Analysis in Smart Contracts: Trends, Challenges and Future Directions

Smart contracts, integral to blockchain ecosystems, enable decentralized applications to execute predefined operations without intermediaries. Their ability to enforce trustless interactions has made them a core component of platforms such as Ethereum. Vulnerabilities such as numerical overflows,...

LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning

Vertical federated learning VFL has become a key paradigm for collaborative machine learning, enabling multiple parties to train models over distributed feature spaces while preserving data privacy. Despite security protocols that defend against external attacks - such as gradient masking and...

Identity Deepfake Threats to Biometric Authentication Systems: Public and Expert Perspectives

Generative AI Gen-AI deepfakes pose a rapidly evolving threat to biometric authentication, yet a significant gap exists between expert understanding of these risks and public perception. This disconnection creates critical vulnerabilities in systems trusted by millions. To bridge this gap, we...

Differentially Private Sparse Linear Regression with Heavy-Tailed Responses

As a fundamental problem in machine learning and differential privacy DP, DP linear regression has been extensively studied. However, most existing methods focus primarily on either regular data distributions or low-dimensional cases with irregular data. To address these limitations, this paper...

ARGOS: Anomaly Recognition and Guarding through O-RAN Sensing

Rogue Base Station RBS attacks, particularly those exploiting downgrade vulnerabilities, remain a persistent threat as 5G Standalone SA deployments are still limited and User Equipment UE manufacturers continue to support legacy network connectivity. This work introduces ARGOS, a comprehensive...

Breaking Data Silos: Towards Open and Scalable Mobility Foundation Models Via Generative Continual Learning

Foundation models have revolutionized fields such as natural language processing and computer vision by enabling general-purpose learning across diverse tasks and datasets. However, building analogous models for human mobility remains challenging due to the privacy-sensitive nature of mobility da...

Can In-Context Reinforcement Learning Recover from Reward Poisoning Attacks?

We study the corruption-robustness of in-context reinforcement learning ICRL, focusing on the Decision-Pretrained Transformer DPT, Lee et al., 2023. To address the challenge of reward poisoning attacks targeting the DPT, we propose a novel adversarial training framework, called Adversarially...

An Efficient Digital Watermarking Technique for Small Scale Devices

In the age of IoT and mobile platforms, ensuring that content stay authentic whilst avoiding overburdening limited hardware is a key problem. This study introduces hybrid Fast Wavelet Transform & Additive Quantization index Modulation FWT-AQIM scheme, a lightweight watermarking approach that...

Rewriting the Budget: a General Framework for Black-Box Attacks under Cost Asymmetry

Traditional decision-based black-box adversarial attacks on image classifiers aim to generate adversarial examples by slightly modifying input images while keeping the number of queries low, where each query involves sending an input to the model and observing its output. Most existing methods...

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems

Retrieval-Augmented Generation RAG systems enhance Large Language Models LLMs by retrieving relevant documents from external corpora before generating responses. This approach significantly expands LLM capabilities by leveraging vast, up-to-date external knowledge. However, this reliance on...

Differentially Private Explanations for Clusters

The dire need to protect sensitive data has led to various flavors of privacy definitions. Among these, Differential privacy DP is considered one of the most rigorous and secure notions of privacy, enabling data analysis while preserving the privacy of data contributors. One of the fundamental...

Dual-Conditional Deep Generation of Network Traffic Data for Network Intrusion Detection System Balancing

Whitepaper called Dual-Conditional Deep Generation Of Network Traffic Data For Network Intrusion Detection System Balancing...

Stochastic Training for Side-Channel Resilient AI

The confidentiality of trained AI models on edge devices is at risk from side-channel attacks exploiting power and electromagnetic emissions. This paper proposes a novel training methodology to enhance resilience against such threats by introducing randomized and interchangeable model...

SDN-Based False Data Detection with Its Mitigation and Machine Learning Robustness for In-Vehicle Networks

As the development of autonomous and connected vehicles advances, the complexity of modern vehicles increases, with numerous Electronic Control Units ECUs integrated into the system. In an in-vehicle network, these ECUs communicate with one another using an standard protocol called Controller Are...