7964 matches found
HeavyWater and SimplexWater: Watermarking Low-Entropy Text Distributions
Large language model LLM watermarks enable authentication of text provenance, curb misuse of machine-generated text, and promote trust in AI systems. Current watermarks operate by changing the next-token predictions output by an LLM. The updated i.e., watermarked predictions depend on random side...
Adapting under Fire: Multi-Agent Reinforcement Learning for Adversarial Drift in Network Security
Evolving attacks are a critical challenge for the long-term success of Network Intrusion Detection Systems NIDS. The rise of these changing patterns has exposed the limitations of traditional network security methods. While signature-based methods are used to detect different types of attacks, th...
Depermissioning Web3: a Permissionless Accountable RPC Protocol for Blockchain Networks
In blockchain networks, so-called "full nodes" serve data to and relay transactions from clients through an RPC interface. This serving layer enables integration of "Web3" data, stored on blockchains, with "Web2" mobile or web applications that cannot directly participate as peers in a blockchain...
The Scales of Justitia: a Comprehensive Survey on Safety Evaluation of LLMs
With the rapid advancement of artificial intelligence technology, Large Language Models LLMs have demonstrated remarkable potential in the field of Natural Language Processing NLP, including areas such as content generation, human-computer interaction, machine translation, and code generation,...
Faraday 5.14.1
Faraday is a tool that introduces a new concept called IPE, or Integrated Penetration-Test Environment. It is a multiuser penetration test IDE designed for distribution, indexation and analysis of the generated data during the process of a security audit. The main purpose of Faraday is to re-use...
Benchmarking Misuse Mitigation against Covert Adversaries
Existing language model safety evaluations focus on overt attacks and low-stakes tasks. Realistic attackers can subvert current safeguards by requesting help on small, benign-seeming tasks across many independent queries. Because individual queries do not appear harmful, the attack is hard to...
SoK: Are Watermarks in LLMs Ready for Deployment?
Large Language Models LLMs have transformed natural language processing, demonstrating impressive capabilities across diverse tasks. However, deploying these models introduces critical risks related to intellectual property violations and potential misuse, particularly as adversaries can imitate...
Hiding in Plain Sight: Query Obfuscation Via Random Multilingual Searches
Modern search engines extensively personalize results by building detailed user profiles based on query history and behaviour. While personalization can enhance relevance, it introduces privacy risks and can lead to filter bubbles. This paper proposes and evaluates a lightweight, client-side quer...
Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents
The rise of Large Language Models LLMs has revolutionized Graphical User Interface GUI automation through LLM-powered GUI agents, yet their ability to process sensitive data with limited human oversight raises significant privacy and security risks. This position paper identifies three key risks ...
Identifying and Understanding Cross-Class Features in Adversarial Training
Adversarial training AT has been considered one of the most effective methods for making deep neural networks robust against adversarial attacks, while the training mechanisms and dynamics of AT remain open research problems. In this paper, we present a novel perspective on studying AT through th...
Evaluating Apple Intelligence'S Writing Tools for Privacy against Large Language Model-Based Inference Attacks: Insights from Early Datasets
The misuse of Large Language Models LLMs to infer emotions from text for malicious purposes, known as emotion inference attacks, poses a significant threat to user privacy. In this paper, we investigate the potential of Apple Intelligence's writing tools, integrated across iPhone, iPad, and...
Dropout-Robust Mechanisms for Differentially Private and Fully Decentralized Mean Estimation
Achieving differentially private computations in decentralized settings poses significant challenges, particularly regarding accuracy, communication cost, and robustness against information leakage. While cryptographic solutions offer promise, they often suffer from high communication overhead or...
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 ...
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...
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...
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...
Synchronic Web Digital Identity: Speculations on the Art of the Possible
As search, social media, and artificial intelligence continue to reshape collective knowledge, the preservation of trust on the public infosphere has become a defining challenge of our time. Given the breadth and versatility of adversarial threats, the best--and perhaps only--defense is an equall...
Packet Storm New Exploits for May, 2025
This archive contains all of the 129 exploits added to Packet Storm in May, 2025...
Align Is Not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
Large Language Models LLMs have evolved into Multimodal Large Language Models MLLMs, significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human intelligence, which processes a variety of data forms beyond just...
Black-Box Crypto Is Useless for Pseudorandom Codes
A pseudorandom code is a keyed error-correction scheme with the property that any polynomial number of encodings appear random to any computationally bounded adversary. We show that the pseudorandomness of any code tolerating a constant rate of random errors cannot be based on black-box reduction...
Developing a Risk Identification Framework for Foundation Model Uses
As foundation models grow in both popularity and capability, researchers have uncovered a variety of ways that the models can pose a risk to the model's owner, user, or others. Despite the efforts of measuring these risks via benchmarks and cataloging them in AI risk taxonomies, there is little...
Nearly-Linear Time Private Hypothesis Selection with the Optimal Approximation Factor
Estimating the density of a distribution from its samples is a fundamental problem in statistics. Hypothesis selection addresses the setting where, in addition to a sample set, we are given $n$ candidate distributions -- referred to as hypotheses -- and the goal is to determine which one best...
A Geometric Square-Based Approach to RSA Integer Factorization
We present a new approach to RSA factorization inspired by geometric interpretations and square differences. This method reformulates the problem in terms of the distance between perfect squares and provides a recurrence relation that allows rapid convergence when the RSA modulus has closely spac...
Video Signature: In-Generation Watermarking for Latent Video Diffusion Models
The rapid development of Artificial Intelligence Generated Content AIGC has led to significant progress in video generation but also raises serious concerns about intellectual property protection and reliable content tracing. Watermarking is a widely adopted solution to this issue, but existing...
Assessing and Enhancing Quantum Readiness in Mobile Apps
Quantum computers threaten widely deployed cryptographic primitives such as RSA, DSA, and ECC. While NIST has released post-quantum cryptographic PQC standards e.g., Kyber, Dilithium, mobile app ecosystems remain largely unprepared for this transition. We present a large-scale binary analysis of...
Amatriciana: Exploiting Temporal GNNs for Robust and Efficient Money Laundering Detection
Money laundering is a financial crime that poses a serious threat to financial integrity and social security. The growing number of transactions makes it necessary to use automatic tools that help law enforcement agencies detect such criminal activity. In this work, we present Amatriciana, a nove...
Security Concerns for Large Language Models: a Survey
Large Language Models LLMs such as GPT-4 and its recent iterations, Google's Gemini, Anthropic's Claude 3 models, and xAI's Grok have caused a revolution in natural language processing, but their capabilities also introduce new security vulnerabilities. In this survey, we provide a comprehensive...
Shadow Defense against Gradient Inversion Attack in Federated Learning
Federated learning FL has emerged as a transformative framework for privacy-preserving distributed training, allowing clients to collaboratively train a global model without sharing their local data. This is especially crucial in sensitive fields like healthcare, where protecting patient data is...
Local Frames: Exploiting Inherited Origins to Bypass Content Blockers
We present a study of how local frames i.e., iframes with non-URL sources like "about:blank" are mishandled by a wide range of popular Web security and privacy tools. As a result, users of these tools remain vulnerable to the very attack techniques they seek to protect against, including browser...
A Reward-Driven Automated Webshell Malicious-Code Generator for Red-Teaming
Whitepaper called A Reward-Driven Automated Webshell Malicious-Code Generator For Red-Teaming...
Talking Transactions: Decentralized Communication through Ethereum Input Data Messages (IDMs)
Can you imagine, blockchain transactions can talk! In this paper, we study how they talk and what they talk about. We focus on the input data field of Ethereum transactions, which is designed to allow external callers to interact with smart contracts. In practice, this field also enables users to...
Machine Learning Models Have a Supply Chain Problem
Powerful machine learning ML models are now readily available online, which creates exciting possibilities for users who lack the deep technical expertise or substantial computing resources needed to develop them. On the other hand, this type of open ecosystem comes with many risks. In this paper...
Private Lossless Multiple Release
Whitepaper called Private Lossless Multiple Release...
Efficient Preimage Approximation for Neural Network Certification
The growing reliance on artificial intelligence in safety- and security-critical applications demands effective neural network certification. A challenging real-world use case is certification against patch attacks'', where adversarial patches or lighting conditions obscure parts of images, for...
On the Intractability of Chaotic Symbolic Walks: toward a Non-Algebraic Post-Quantum Hardness Assumption
Most classical and post-quantum cryptographic assumptions, including integer factorization, discrete logarithms, and Learning with Errors LWE, rely on algebraic structures such as rings or vector spaces. While mathematically powerful, these structures can be exploited by quantum algorithms or...
Towards a DSL for Hybrid Secure Computation
Fully homomorphic encryption FHE and trusted execution environments TEE are two approaches to provide confidentiality during data processing. Each approach has its own strengths and weaknesses. In certain scenarios, computations can be carried out in a hybrid environment, using both FHE and TEE...
BLACKOUT: Data-Oblivious Computation with Blinded Capabilities
Lack of memory-safety and exposure to side channels are two prominent, persistent challenges for the secure implementation of software. Memory-safe programming languages promise to significantly reduce the prevalence of memory-safety bugs, but make it more difficult to implement...
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...
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...
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...
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...
Penetration Testing for System Security: Methods and Practical Approaches
Penetration testing refers to the process of simulating hacker attacks to evaluate the security of information systems . This study aims not only to clarify the theoretical foundations of penetration testing but also to explain and demonstrate the complete testing process, including how network...
Co-Evolutionary Dynamics of Attack and Defence in Cybersecurity
In the evolving digital landscape, it is crucial to study the dynamics of cyberattacks and defences. This study uses an Evolutionary Game Theory EGT framework to investigate the evolutionary dynamics of attacks and defences in cyberspace. We develop a two-population asymmetric game between attack...
A Study of Semi-Fungible Token Based Wi-Fi Access Control
Current Wi-Fi authentication methods face issues such as insufficient security, user privacy leakage, high management costs, and difficulty in billing. To address these challenges, a Wi-Fi access control solution based on blockchain smart contracts is proposed. Firstly, semi-fungible Wi-Fi tokens...
LAMDA: a Longitudinal Android Malware Benchmark for Concept Drift Analysis
Machine learning ML-based malware detection systems often fail to account for the dynamic nature of real-world training and test data distributions. In practice, these distributions evolve due to frequent changes in the Android ecosystem, adversarial development of new malware families, and the...
Toward Malicious Clients Detection in Federated Learning
Federated learning FL enables multiple clients to collaboratively train a global machine learning model without sharing their raw data. However, the decentralized nature of FL introduces vulnerabilities, particularly to poisoning attacks, where malicious clients manipulate their local models to...
Adaptively Secure Distributed Broadcast Encryption with Linear-Size Public Parameters
Distributed broadcast encryption DBE is a variant of broadcast encryption BE that can efficiently transmit a message to a subset of users, in which users independently generate user private keys and user public keys instead of a central trusted authority generating user keys. In this paper, we...
Privacy-Preserving Bathroom Monitoring for Elderly Emergencies Using PIR and LiDAR Sensors
In-home elderly monitoring requires systems that can detect emergency events - such as falls or prolonged inactivity - while preserving privacy and requiring no user input. These systems must be embedded into the surrounding environment, capable of capturing activity, and responding promptly. Thi...