Beyond the Worst Case: Extending Differential Privacy Guarantees to Realistic Adversaries

Differential Privacy DP is a family of definitions that bound the worst-case privacy leakage of a mechanism. One important feature of the worst-case DP guarantee is it naturally implies protections against adversaries with less prior information, more sophisticated attack goals, and complex...

Towards Privacy-Preserving and Personalized Smart Homes Via Tailored Small Language Models

Large Language Models LLMs have showcased remarkable generalizability in language comprehension and hold significant potential to revolutionize human-computer interaction in smart homes. Existing LLM-based smart home assistants typically transmit user commands, along with user profiles and home...

WinRAR Directory Traversal

WinRAR suffers from a directory traversal vulnerability that allows an attacker to place files outside the intended extraction directory when a user extracts a specially crafted .rar archive. Versions prior to 7.12 are affected...

A Formal Rebuttal of "The Blockchain Trilemma: a Formal Proof of the Inherent Trade-Offs among Decentralization, Security, and Scalability"

This paper presents a comprehensive refutation of the so-called "blockchain trilemma," a widely cited but formally ungrounded claim asserting an inherent trade-off between decentralisation, security, and scalability in blockchain protocols. Through formal analysis, empirical evidence, and detaile...

GPUHammer: Rowhammer Attacks on GPU Memories Are Practical

Rowhammer is a read disturbance vulnerability in modern DRAM that causes bit-flips, compromising security and reliability. While extensively studied on Intel and AMD CPUs with DDR and LPDDR memories, its impact on GPUs using GDDR memories, critical for emerging machine learning applications,...

Agent Safety Alignment Via Reinforcement Learning

The emergence of autonomous Large Language Model LLM agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to both user-initiated threats e.g., adversarial prompts and...

Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking

With the rise of social media, vast amounts of user-uploaded videos e.g., YouTube are utilized as training data for Visual Object Tracking VOT. However, the VOT community has largely overlooked video data-privacy issues, as many private videos have been collected and used for training commercial...

Autonomous AI-Based Cybersecurity Framework for Critical Infrastructure: Real-Time Threat Mitigation

Critical infrastructure systems, including energy grids, healthcare facilities, transportation networks, and water distribution systems, are pivotal to societal stability and economic resilience. However, the increasing interconnectivity of these systems exposes them to various cyber threats,...

Mitigating Watermark Stealing Attacks in Generative Models Via Multi-Key Watermarking

Watermarking offers a promising solution for GenAI providers to establish the provenance of their generated content. A watermark is a hidden signal embedded in the generated content, whose presence can later be verified using a secret watermarking key. A threat to GenAI providers are \emphwaterma...

libxslt xmlNode.psvi Type Confusion

libxslt suffers from a type confusion vulnerability in xmlNode.psvi between stylesheet and source nodes...

Invariant-Based Robust Weights Watermark for Large Language Models

Watermarking technology has gained significant attention due to the increasing importance of intellectual property IP rights, particularly with the growing deployment of large language models LLMs on billions resource-constrained edge devices. To counter the potential threats of IP theft by...

Quantum Properties Trojans (QuPTs) for Attacking Quantum Neural Networks

Quantum neural networks QNN hold immense potential for the future of quantum machine learning QML. However, QNN security and robustness remain largely unexplored. In this work, we proposed novel Trojan attacks based on the quantum computing properties in a QNN-based binary classifier. Our propose...

EinHops: Einsum Notation for Expressive Homomorphic Operations on RNS-CKKS Tensors

Fully Homomorphic Encryption FHE is an encryption scheme that allows for computation to be performed directly on encrypted data, effectively closing the loop on secure and outsourced computing. Data is encrypted not only during rest and transit, but also during processing. However, FHE provides a...

GNU Transport Layer Security Library 3.8.10

GnuTLS is a secure communications library implementing the SSL and TLS protocols and technologies around them. It provides a simple C language application programming interface API to access the secure communications protocols, as well as APIs to parse and write X.509, PKCS 12, OpenPGP, and other...

Semi-Fragile Watermarking of Remote Sensing Images Using DWT, Vector Quantization and Automatic Tiling

A semi-fragile watermarking scheme for multiple band images is presented in this article. We propose to embed a mark into remote sensing images applying a tree-structured vector quantization approach to the pixel signatures instead of processing each band separately. The signature of the...

WatchWitch: Interoperability, Privacy, and Autonomy for the Apple Watch

Smartwatches such as the Apple Watch collect vast amounts of intimate health and fitness data as we wear them. Users have little choice regarding how this data is processed: The Apple Watch can only be used with Apple's iPhones, using their software and their cloud services. We are the first to...

AdeptHEQ-FL: Adaptive Homomorphic Encryption for Federated Learning of Hybrid Classical-Quantum Models with Dynamic Layer Sparing

Federated Learning FL faces inherent challenges in balancing model performance, privacy preservation, and communication efficiency, especially in non-IID decentralized environments. Recent approaches either sacrifice formal privacy guarantees, incur high overheads, or overlook quantum-enhanced...

Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy

Differentially private DP mechanisms are difficult to interpret and calibrate because existing methods for mapping standard privacy parameters to concrete privacy risks -- re-identification, attribute inference, and data reconstruction -- are both overly pessimistic and inconsistent. In this work...

Analytic Rényi Entropy Bounds for Device-Independent Cryptography

Device-independent DI cryptography represents the highest level of security, enabling cryptographic primitives to be executed safely on uncharacterized devices. Moreover, with successful proof-of-concept demonstrations in randomness expansion, randomness amplification, and quantum key distributio...

Microsoft Windows 11 x64 Reverse TCP Shellcode

564 bytes small Microsoft Windows 11 x64 reverse TCP shellcode...

RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation

Retrieval-Augmented Generation RAG enhances large language models LLMs by retrieving external data to mitigate hallucinations and outdated knowledge issues. Benefiting from the strong ability in facilitating diverse data sources and supporting faithful reasoning, knowledge graphs KGs have been...

Clio-X: AWeb3 Solution for Privacy-Preserving AI Access to Digital Archives

As archives turn to artificial intelligence to manage growing volumes of digital records, privacy risks inherent in current AI data practices raise critical concerns about data sovereignty and ethical accountability. This paper explores how privacy-enhancing technologies PETs and Web3 architectur...

BarkBeetle: Stealing Decision Tree Models with Fault Injection

Machine learning models, particularly decision trees DTs, are widely adopted across various domains due to their interpretability and efficiency. However, as ML models become increasingly integrated into privacy-sensitive applications, concerns about their confidentiality have grown, particularly...

Kigen eUICC Type Confusion

Security Explorations has broken the security of Kigen eUICC card with GSMA consumer certificates installed into it. The eUICC card makes it possible to install the so called eSIM profiles into target chip. eSIM profiles are software representations of mobile subscriptions. For many years such...

Understanding Malware Propagation Dynamics through Scientific Machine Learning

Accurately modeling malware propagation is essential for designing effective cybersecurity defenses, particularly against adaptive threats that evolve in real time. While traditional epidemiological models and recent neural approaches offer useful foundations, they often fail to fully capture the...

PotentRegion4MalDetect: Advanced Features from Potential Malicious Regions for Malware Detection

Malware developers exploit the fact that most detection models focus on the entire binary to extract the feature rather than on the regions of potential maliciousness. Therefore, they reverse engineer a benign binary and inject malicious code into it. This obfuscation technique circumvents the...

Automated Attack Testflow Extraction from Cyber Threat Report Using BERT for Contextual Analysis

In the ever-evolving landscape of cybersecurity, the rapid identification and mitigation of Advanced Persistent Threats APTs is crucial. Security practitioners rely on detailed threat reports to understand the tactics, techniques, and procedures TTPs employed by attackers. However, manually...

On the Impossibility of Separating Intelligence from Judgment: the Computational Intractability of Filtering for AI Alignment

With the increased deployment of large language models LLMs, one concern is their potential misuse for generating harmful content. Our work studies the alignment challenge, with a focus on filters to prevent the generation of unsafe information. Two natural points of intervention are the filterin...

FedP3E: Privacy-Preserving Prototype Exchange for Non-IID IoT Malware Detection in Cross-Silo Federated Learning

As IoT ecosystems continue to expand across critical sectors, they have become prominent targets for increasingly sophisticated and large-scale malware attacks. The evolving threat landscape, combined with the sensitive nature of IoT-generated data, demands detection frameworks that are both...

Privacy-Utility-Fairness: a Balanced Approach to Vehicular-Traffic Management System

Location-based vehicular traffic management faces significant challenges in protecting sensitive geographical data while maintaining utility for traffic management and fairness across regions. Existing state-of-the-art solutions often fail to meet the required level of protection against linkage...

AI Agent Smart Contract Exploit Generation

We present A1, an agentic execution driven system that transforms any LLM into an end-to-end exploit generator. A1 has no hand-crafted heuristics and provides the agent with six domain-specific tools that enable autonomous vulnerability discovery. The agent can flexibly leverage these tools to...

Disa: Accurate Learning-Based Static Disassembly with Attentions

For reverse engineering related security domains, such as vulnerability detection, malware analysis, and binary hardening, disassembly is crucial yet challenging. The fundamental challenge of disassembly is to identify instruction and function boundaries. Classic approaches rely on file-format...

Shuffling for Semantic Secrecy

Deep learning draws heavily on the latest progress in semantic communications. The present paper aims to examine the security aspect of this cutting-edge technique from a novel shuffling perspective. Our goal is to improve upon the conventional secure coding scheme to strike a desirable tradeoff...

Wrapless: the Trustless Lending Protocol on Top of Bitcoin

This paper presents Wrapless -- a lending protocol that enables the collateralization of bitcoins without requiring a trusted wrapping mechanism. The protocol facilitates a "loan channel" on the Bitcoin blockchain, allowing bitcoins to be locked as collateral for loans issued on any blockchain th...

Approximating Euler Totient Function Using Linear Regression on RSA Moduli

The security of the RSA cryptosystem is based on the intractability of computing Euler's totient function phin for large integers n. Although deriving phin deterministically remains computationally infeasible for cryptographically relevant bit lengths, and machine learning presents a promising...

On Jailbreaking Quantized Language Models through Fault Injection Attacks

The safety alignment of Language Models LMs is a critical concern, yet their integrity can be challenged by direct parameter manipulation attacks, such as those potentially induced by fault injection. As LMs are increasingly deployed using low-precision quantization for efficiency, this paper...

Image Can Bring Your Memory Back: a Novel Multi-Modal Guided Attack against Image Generation Model Unlearning

Whitepaper called Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack Against Image Generation Model Unlearning...

Subgraph Counting under Edge Local Differential Privacy Based on Noisy Adjacency Matrix

When analyzing connection patterns within graphs, subgraph counting serves as an effective and fundamental approach. Edge-local differential privacy edge-LDP and shuffle model have been employed to achieve subgraph counting under a privacy-preserving situation. Existing algorithms are plagued by...

LDP$^3$: an Extensible and Multi-Threaded Toolkit for Local Differential Privacy Protocols and Post-Processing Methods

Local differential privacy LDP has become a prominent notion for privacy-preserving data collection. While numerous LDP protocols and post-processing PP methods have been developed, selecting an optimal combination under different privacy budgets and datasets remains a challenge. Moreover, the la...

Automated Reasoning for Vulnerability Management by Design

For securing systems, it is essential to manage their vulnerability posture and design appropriate security controls. Vulnerability management allows to proactively address vulnerabilities by incorporating pertinent security controls into systems designs. Current vulnerability management approach...

The Impact of Event Data Partitioning on Privacy-Aware Process Discovery

Information systems support the execution of business processes. The event logs of these executions generally contain sensitive information about customers, patients, and employees. The corresponding privacy challenges can be addressed by anonymizing the event logs while still retaining utility f...

Immutability Does Not Guarantee Trust: a Formal and Logical Refutation

It is frequently claimed in blockchain discourse that immutability guarantees trust. This paper rigorously refutes that assertion. We define immutability as the cryptographic persistence of historical states in an append-only data structure and contrast it with trust, understood as a rational...

Enhancing LLM Watermark Resilience against Both Scrubbing and Spoofing Attacks

Watermarking is a promising defense against the misuse of large language models LLMs, yet it remains vulnerable to scrubbing and spoofing attacks. This vulnerability stems from an inherent trade-off governed by watermark window size: smaller windows resist scrubbing better but are easier to...

Asynchronous Event Error-Minimizing Noise for Safeguarding Event Dataset

With more event datasets being released online, safeguarding the event dataset against unauthorized usage has become a serious concern for data owners. Unlearnable Examples are proposed to prevent the unauthorized exploitation of image datasets. However, it's unclear how to create unlearnable...

Detection of Intelligent Tampering in Wireless Electrocardiogram Signals Using Hybrid Machine Learning

With the proliferation of wireless electrocardiogram ECG systems for health monitoring and authentication, protecting signal integrity against tampering is becoming increasingly important. This paper analyzes the performance of CNN, ResNet, and hybrid Transformer-CNN models for tamper detection. ...

A Formal Refutation of the Blockchain Trilemma

The so-called blockchain trilemma asserts the impossibility of simultaneously achieving scalability, security, and decentralisation within a single blockchain protocol. In this paper, we formally refute that proposition. Employing predicate logic, formal automata theory, computational complexity...

Generalized and Unified Equivalences between Hardness and Pseudoentropy

Pseudoentropy characterizations provide a quantitatively precise demonstration of the close relationship between computational hardness and computational randomness. We prove a unified pseudoentropy characterization that generalizes and strengthens previous results for both uniform and non-unifor...

HEMA: a Hands-On Exploration Platform for MEMS Sensor Attacks

Automotive safety and security are paramount in the rapidly advancing landscape of vehicular technology. Building safe and secure vehicles demands a profound understanding of automotive systems, particularly in safety and security. Traditional learning approaches, such as reading materials or...

Enter, Exit, Page Fault, Leak: Testing Isolation Boundaries for Microarchitectural Leaks

CPUs provide isolation mechanisms like virtualization and privilege levels to protect software. Yet these focus on architectural isolation while typically overlooking microarchitectural side channels, exemplified by Meltdown and Foreshadow. Software must therefore supplement architectural defense...

Bridging AI and Software Security: a Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms

Large Language Model LLM agents face security vulnerabilities spanning AI-specific and traditional software domains, yet current research addresses these separately. This study bridges this gap through comparative evaluation of Function Calling architecture and Model Context Protocol MCP deployme...