Unveiling Impact of Frequency Components on Membership Inference Attacks for Diffusion Models

Diffusion models have achieved tremendous success in image generation, but they also raise significant concerns regarding privacy and copyright issues. Membership Inference Attacks MIAs are designed to ascertain whether specific data were utilized during a model's training phase. As current MIAs...

JavaSith: a Client-Side Framework for Analyzing Potentially Malicious Extensions in Browsers, VS Code, and NPM Packages

Modern software supply chains face an increasing threat from malicious code hidden in trusted components such as browser extensions, IDE extensions, and open-source packages. This paper introduces JavaSith, a novel client-side framework for analyzing potentially malicious extensions in web...

TrojanStego: Your Language Model Can Secretly Be a Steganographic Privacy Leaking Agent

As large language models LLMs become integrated into sensitive workflows, concerns grow over their potential to leak confidential information. We propose TrojanStego, a novel threat model in which an adversary fine-tunes an LLM to embed sensitive context information into natural-looking outputs v...

AdInject: Real-World Black-Box Attacks on Web Agents Via Advertising Delivery

Vision-Language Model VLM based Web Agents represent a significant step towards automating complex tasks by simulating human-like interaction with websites. However, their deployment in uncontrolled web environments introduces significant security vulnerabilities. Existing research on adversarial...

Uncovering Black-Hat SEO Based Fake E-Commerce Scam Groups from Their Redirectors and Websites

While law enforcements agencies and cybercrime researchers are working hard, fake E-commerce scam is still a big threat to Internet users. One of the major techniques to victimize users is luring them by black-hat search-engine-optimization SEO; making search engines display their lure pages as i...

Evaluating AI Cyber Capabilities with Crowdsourced Elicitation

As AI systems become increasingly capable, understanding their offensive cyber potential is critical for informed governance and responsible deployment. However, it's hard to accurately bound their capabilities, and some prior evaluations dramatically underestimated them. The art of extracting...

Respond to Change with Constancy: Instruction-Tuning with LLM for Non-I.I.D. Network Traffic Classification

Encrypted traffic classification is highly challenging in network security due to the need for extracting robust features from content-agnostic traffic data. Existing approaches face critical issues: i Distribution drift, caused by reliance on the closedworld assumption, limits adaptability to...

Grassroots Consensus

Grassroots platforms aim to offer an egalitarian alternative to global platforms -- centralized/autocratic and decentralized/plutocratic alike. Within the grassroots architecture, consensus is needed to realize platforms that employ digital social contracts, which are like smart contracts except...

The Feasibility of Topic-Based Watermarking on Academic Peer Reviews

Large language models LLMs are increasingly integrated into academic workflows, with many conferences and journals permitting their use for tasks such as language refinement and literature summarization. However, their use in peer review remains prohibited due to concerns around confidentiality...

Preventing Adversarial AI Attacks against Autonomous Situational Awareness: a Maritime Case Study

Adversarial artificial intelligence AI attacks pose a significant threat to autonomous transportation, such as maritime vessels, that rely on AI components. Malicious actors can exploit these systems to deceive and manipulate AI-driven operations. This paper addresses three critical research...

IRCopilot: Automated Incident Response with Large Language Models

Incident response plays a pivotal role in mitigating the impact of cyber attacks. In recent years, the intensity and complexity of global cyber threats have grown significantly, making it increasingly challenging for traditional threat detection and incident response methods to operate effectivel...

A Joint Reconstruction-Triplet Loss Autoencoder Approach Towards Unseen Attack Detection in IoV Networks

Internet of Vehicles IoV systems, while offering significant advancements in transportation efficiency and safety, introduce substantial security vulnerabilities due to their highly interconnected nature. These dynamic systems produce massive amounts of data between vehicles, infrastructure, and...

VideoMarkBench: Benchmarking Robustness of Video Watermarking

The rapid development of video generative models has led to a surge in highly realistic synthetic videos, raising ethical concerns related to disinformation and copyright infringement. Recently, video watermarking has been proposed as a mitigation strategy by embedding invisible marks into...

BitHydra: Towards Bit-Flip Inference Cost Attack against Large Language Models

Large language models LLMs have shown impressive capabilities across a wide range of applications, but their ever-increasing size and resource demands make them vulnerable to inference cost attacks, where attackers induce victim LLMs to generate the longest possible output content. In this paper,...

ColorGo: Directed Concolic Execution

Whitepaper called ColorGo: Directed Concolic Execution...

Effect of Noise and Topologies on Multi-Photon Quantum Protocols

Quantum-augmented networks aim to use quantum phenomena to improve detection and protection against malicious actors in a classical communication network. This may include multiplexing quantum signals into classical fiber optical channels and incorporating purely quantum links alongside classical...

DP-RTFL: Differentially Private Resilient Temporal Federated Learning for Trustworthy AI in Regulated Industries

Federated Learning FL has emerged as a critical paradigm for enabling privacy-preserving machine learning, particularly in regulated sectors such as finance and healthcare. However, standard FL strategies often encounter significant operational challenges related to fault tolerance, system...

WordPress Order Delivery Date Missing Authorization

WordPress Order Delivery Date plugin versions prior to 12.3.1 have missing authorization and cross site request forgery vulnerabilities surrounding the importing of settings...

Multi-Photon QKD for Practical Quantum Networks

Quantum key distribution QKD will most likely be an integral part of any practical quantum network in the future. However, not all QKD protocols can be used in today's networks because of the lack of single-photon emitters and noisy intermediate quantum hardware. Attenuated-photon transmission,...

Watermarking without Standards Is Not AI Governance

Watermarking has emerged as a leading technical proposal for attributing generative AI content and is increasingly cited in global governance frameworks. This paper argues that current implementations risk serving as symbolic compliance rather than delivering effective oversight. We identify a...

Enhancing JavaScript Malware Detection through Weighted Behavioral DFAs

This work addresses JavaScript malware detection to enhance client-side web application security with a behavior-based system. The ability to detect malicious JavaScript execution sequences is a critical problem in modern web security as attack techniques become more sophisticated. This study...

Red-Teaming Text-To-Image Systems by Rule-Based Preference Modeling

Text-to-image T2I models raise ethical and safety concerns due to their potential to generate inappropriate or harmful images. Evaluating these models' security through red-teaming is vital, yet white-box approaches are limited by their need for internal access, complicating their use with...

SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA

Federated fine-tuning of large language models LLMs is critical for improving their performance in handling domain-specific tasks. However, prior work has shown that clients' private data can actually be recovered via gradient inversion attacks. Existing privacy preservation techniques against su...

PrivATE: Differentially Private Confidence Intervals for Average Treatment Effects

The average treatment effect ATE is widely used to evaluate the effectiveness of drugs and other medical interventions. In safety-critical applications like medicine, reliable inferences about the ATE typically require valid uncertainty quantification, such as through confidence intervals CIs...

A Hitchhiker'S Guide to Privacy-Preserving Cryptocurrencies: a Survey on Anonymity, Confidentiality, and Auditability

Cryptocurrencies and central bank digital currencies CBDCs are reshaping the monetary landscape, offering transparency and efficiency while raising critical concerns about user privacy and regulatory compliance. This survey provides a comprehensive and technically grounded overview of...

Backdoors in DRL: Four Environments Focusing on In-Distribution Triggers

Backdoor attacks, or trojans, pose a security risk by concealing undesirable behavior in deep neural network models. Open-source neural networks are downloaded from the internet daily, possibly containing backdoors, and third-party model developers are common. To advance research on backdoor atta...

M3S-UPD: Efficient Multi-Stage Self-Supervised Learning for Fine-Grained Encrypted Traffic Classification with Unknown Pattern Discovery

The growing complexity of encrypted network traffic presents dual challenges for modern network management: accurate multiclass classification of known applications and reliable detection of unknown traffic patterns. Although deep learning models show promise in controlled environments, their...

Online Voting Using Point to MultiPoint Quantum Key Distribution Via Passive Optical Networks

We propose using Point-to-Multipoint quantum key distribution QKD via time division multiplexing TDM and wavelength division multiplexing WDM in passive optical networks PON to improve the security of online voting systems...

CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models

Retrieval-Augmented Generation RAG enhances large language models LLMs by incorporating external knowledge, but its openness introduces vulnerabilities that can be exploited by poisoning attacks. Existing poisoning methods for RAG systems have limitations, such as poor generalization and lack of...

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

Deep Neural Networks DNNs have achieved widespread success yet remain prone to adversarial attacks. Typically, such attacks either involve frequent queries to the target model or rely on surrogate models closely mirroring the target model -- often trained with subsets of the target model's traini...

A Framework for Combined Transaction Posting and Pricing for Layer 2 Blockchains

This paper presents a comprehensive framework for transaction posting and pricing in Layer 2 L2 blockchain systems, focusing on challenges stemming from fluctuating Layer 1 L1 gas fees and the congestion issues within L2 networks. Existing methods have focused on the problem of optimal posting...

A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?

Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of \emphComputer-Using Agents CUAs, capable of autonomously...

Private Geometric Median in Nearly-Linear Time

Whitepaper called Private Geometric Median In Nearly-Linear Time...

Differential Privacy Analysis of Decentralized Gossip Averaging under Varying Threat Models

Fully decentralized training of machine learning models offers significant advantages in scalability, robustness, and fault tolerance. However, achieving differential privacy DP in such settings is challenging due to the absence of a central aggregator and varying trust assumptions among nodes. I...

EarthOL: a Proof-Of-Human-Contribution Consensus Protocol -- Addressing Fundamental Challenges in Decentralized Value Assessment with Enhanced Verification and Security Mechanisms

This paper introduces EarthOL, a novel consensus protocol that attempts to replace computational waste in blockchain systems with verifiable human contributions within bounded domains. While recognizing the fundamental impossibility of universal value assessment, we propose a domain-restricted...

Language of Network: a Generative Pre-Trained Model for Encrypted Traffic Comprehension

The increasing demand for privacy protection and security considerations leads to a significant rise in the proportion of encrypted network traffic. Since traffic content becomes unrecognizable after encryption, accurate analysis is challenging, making it difficult to classify applications and...

Weak-Jamming Detection in IEEE 802.11 Networks: Techniques, Scenarios and Mobility

State-of-the-art solutions detect jamming attacks ex-post, i.e., only when jamming has already disrupted the wireless communication link. In many scenarios, e.g., mobile networks or static deployments distributed over a large geographical area, it is often desired to detect jamming at the early...

Semantic-Preserving Adversarial Attacks on LLMs: an Adaptive Greedy Binary Search Approach

Large Language Models LLMs increasingly rely on automatic prompt engineering in graphical user interfaces GUIs to refine user inputs and enhance response accuracy. However, the diversity of user requirements often leads to unintended misinterpretations, where automated optimizations distort...

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks

Large language models LLMs have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit harmful outputs. Despite growing efforts in LLM safety research, existing evaluations are often fragmented, focused on...

USB: a Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models

Despite their remarkable achievements and widespread adoption, Multimodal Large Language Models MLLMs have revealed significant security vulnerabilities, highlighting the urgent need for robust safety evaluation benchmarks. Existing MLLM safety benchmarks, however, fall short in terms of data...

Phare: a Safety Probe for Large Language Models

Ensuring the safety of large language models LLMs is critical for responsible deployment, yet existing evaluations often prioritize performance over identifying failure modes. We introduce Phare, a multilingual diagnostic framework to probe and evaluate LLM behavior across three critical...

Poison in the Well: Feature Embedding Disruption in Backdoor Attacks

Backdoor attacks embed malicious triggers into training data, enabling attackers to manipulate neural network behavior during inference while maintaining high accuracy on benign inputs. However, existing backdoor attacks face limitations manifesting in excessive reliance on training data, poor...

TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks

Verification of the integrity of deep learning inference is crucial for understanding whether a model is being applied correctly. However, such verification typically requires access to model weights and potentially sensitive or private training data. So-called Zero-knowledge Succinct...

F5 BIG-IP iControl REST Code Execution

This is an improved version of horizon3ai's F5 BIG-IP iControl REST exploit that provides an interactive shell to run remote commands...

Novel Loss-Enhanced Universal Adversarial Patches for Sustainable Speaker Privacy

Deep learning voice models are commonly used nowadays, but the safety processing of personal data, such as human identity and speech content, remains suspicious. To prevent malicious user identification, speaker anonymization methods were proposed. Current methods, particularly based on universal...

Exposing Go's Hidden Bugs: a Novel Concolic Framework

The widespread adoption of the Go programming language in infrastructure backends and blockchain projects has heightened the need for improved security measures. Established techniques such as unit testing, static analysis, and program fuzzing provide foundational protection mechanisms. Although...

Engineering Trustworthy Machine-Learning Operations with Zero-Knowledge Proofs

As Artificial Intelligence AI systems, particularly those based on machine learning ML, become integral to high-stakes applications, their probabilistic and opaque nature poses significant challenges to traditional verification and validation methods. These challenges are exacerbated in regulated...

Lifelong Safety Alignment for Language Models

LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more critical to prepare LLMs for unseen attacks that may arise duri...

Strengthening Cybersecurity Resilience in Agriculture through Educational Interventions: a Case Study of the Ponca Tribe of Nebraska

The increasing digitization of agricultural operations has introduced new cybersecurity challenges for the farming community. This paper introduces an educational intervention called Cybersecurity Improvement Initiative for Agriculture CIIA, which aims to strengthen cybersecurity awareness and...

Capability-Based Scaling Laws for LLM Red-Teaming

As large language models grow in capability and agency, identifying vulnerabilities through red-teaming becomes vital for safe deployment. However, traditional prompt-engineering approaches may prove ineffective once red-teaming turns into a weak-to-strong problem, where target models surpass...