Synopsis: Secure and Private Trend Inference from Encrypted Semantic Embeddings

WhatsApp and many other commonly used communication platforms guarantee end-to-end encryption E2EE, which requires that service providers lack the cryptographic keys to read communications on their own platforms. WhatsApp's privacy-preserving design makes it difficult to study important phenomena...

Quantum Hilbert Transform

The Hilbert transform has been one of the foundational transforms in signal processing, finding it's way into multiple disciplines from cryptography to biomedical sciences. However, there does not exist any quantum analogue for the Hilbert transform. In this work, we introduce a formulation for t...

Quasi-Periodic Optical Key-Enabled Hybrid Cryptography: Merging Diffractive Physics and Deep Learning for High-Dimensional Security

Optical encryption inherently provides strong security advantages, with hybrid optoelectronic systems offering additional degrees of freedom by integrating optical and algorithmic domains. However, existing optical encryption schemes heavily rely on electronic computation, limiting overall...

Towards a Global Quantum Internet: a Review of Challenges Facing Aerial Quantum Networks

Quantum networks use principles of quantum physics to create secure communication networks. Moving these networks off the ground using drones, balloons, or satellites could help increase the scalability of these networks. This article reviews how such aerial links work, what makes them difficult ...

Practical Bayes-Optimal Membership Inference Attacks

We develop practical and theoretically grounded membership inference attacks MIAs against both independent and identically distributed i.i.d. data and graph-structured data. Building on the Bayesian decision-theoretic framework of Sablayrolles et al., we derive the Bayes-optimal membership...

Private Lossless Multiple Release

Whitepaper called Private Lossless Multiple Release...

AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous work has shown that current LLM-based agents execute...

A Comparative Study of Fuzzers and Static Analysis Tools for Finding Memory Unsafety in C and C++

Even today, over 70% of security vulnerabilities in critical software systems result from memory safety violations. To address this challenge, fuzzing and static analysis are widely used automated methods to discover such vulnerabilities. Fuzzing generates random program inputs to identify faults...

Transformers for Secure Hardware Systems: Applications, Challenges, and Outlook

The rise of hardware-level security threats, such as side-channel attacks, hardware Trojans, and firmware vulnerabilities, demands advanced detection mechanisms that are more intelligent and adaptive. Traditional methods often fall short in addressing the complexity and evasiveness of modern...

Eve File Disclosure / Code Execution

Eve versions prior to 0.7.5 blind remote code execution proof of concept that retrieves files...

WordPress File Away 3.9.9.0.1 Arbitrary File Read

The File Away plugin for WordPress is vulnerable to unauthorized access of data due to a missing capability check on the ajax function in all versions up to, and including, 3.9.9.0.1. This makes it possible for unauthenticated attackers, leveraging the use of a reversible weak algorithm, to read...

Operationalizing CaMeL: Strengthening LLM Defenses for Enterprise Deployment

CaMeL Capabilities for Machine Learning introduces a capability-based sandbox to mitigate prompt injection attacks in large language model LLM agents. While effective, CaMeL assumes a trusted user prompt, omits side-channel concerns, and incurs performance tradeoffs due to its dual-LLM design. Th...

Privacy-Preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models

Prompt learning is a crucial technique for adapting pre-trained multimodal language models MLLMs to user tasks. Federated prompt personalization FPP is further developed to address data heterogeneity and local overfitting, however, it exposes personalized prompts - valuable intellectual assets - ...

Jailbreak Distillation: Renewable Safety Benchmarking

Large language models LLMs are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation JBDistill, a novel benchmark construction framework that "distills" jailbreak attacks into high-quality and easily-updatable safety...

WordPress Likes and Dislikes 1.0.0 SQL Injection

WordPress Likes and Dislikes plugin versions 1.0.0 and below suffer from an unauthenticated remote SQL injection vulnerability...

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...

RedisBloom 2.6.12 Integer Overflow

There is an integer overflow vulnerability in RedisBloom version 2.6.12, which is a module used in redis. The integer overflow vulnerability allows an attacker a redis client which knows the password to allocate memory in the heap lesser than the required memory due to wraparound. Then read and...

Chainless Apps: a Modular Framework for Building Apps with Web2 Capability and Web3 Trust

Modern blockchain applications are often constrained by a trade-off between user experience and trust. Chainless Apps present a new paradigm of application architecture that separates execution, trust, bridging, and settlement into distinct compostable layers. This enables app-specific sequencing...

TensorShield: Safeguarding On-Device Inference by Shielding Critical DNN Tensors with TEE

To safeguard user data privacy, on-device inference has emerged as a prominent paradigm on mobile and Internet of Things IoT devices. This paradigm involves deploying a model provided by a third party on local devices to perform inference tasks. However, it exposes the private model to two primar...

A Comprehensive Real-World Assessment of Audio Watermarking Algorithms: Will They Survive Neural Codecs?

We introduce the Robust Audio Watermarking Benchmark RAW-Bench, a benchmark for evaluating deep learning-based audio watermarking methods with standardized and systematic comparisons. To simulate real-world usage, we introduce a comprehensive audio attack pipeline with various distortions such as...

Private Rate-Constrained Optimization with Applications to Fair Learning

Many problems in trustworthy ML can be formulated as minimization of the model error under constraints on the prediction rates of the model for suitably-chosen marginals, including most group fairness constraints demographic parity, equality of odds, etc.. In this work, we study such constrained...

Test-Time Immunization: a Universal Defense Framework against Jailbreaks for (Multimodal) Large Language Models

While multimodal large language models LLMs have attracted widespread attention due to their exceptional capabilities, they remain vulnerable to jailbreak attacks. Various defense methods are proposed to defend against jailbreak attacks, however, they are often tailored to specific types of...

GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidance

DNA, encoding genetic instructions for almost all living organisms, fuels groundbreaking advances in genomics and synthetic biology. Recently, DNA Foundation Models have achieved success in designing synthetic functional DNA sequences, even whole genomes, but their susceptibility to jailbreaking...

BPMN to Smart Contract by Business Analyst

This paper addresses the challenge of creating smart contracts for applications represented using Business Process Management and Notation BPMN models. In our prior work we presented a methodology that automates the generation of smart contracts from BPMN models. This approach abstracts the BPMN...

A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Control

Traditional Identity and Access Management IAM systems, primarily designed for human users or static machine identities via protocols such as OAuth, OpenID Connect OIDC, and SAML, prove fundamentally inadequate for the dynamic, interdependent, and often ephemeral nature of AI agents operating at...

Spa-VLM: Stealthy Poisoning Attacks on RAG-Based VLM

With the rapid development of the Vision-Language Model VLM, significant progress has been made in Visual Question Answering VQA tasks. However, existing VLM often generate inaccurate answers due to a lack of up-to-date knowledge. To address this issue, recent research has introduced...

Securing the Software Package Supply Chain for Critical Systems

Software systems have grown as an indispensable commodity used across various industries, and almost all essential services depend on them for effective operation. The software is no longer an independent or stand-alone piece of code written by a developer but rather a collection of packages...

Smart Contracts for SMEs and Large Companies

Research on blockchains addresses multiple issues, with one being writing smart contracts. In our previous research we described methodology and a tool to generate, in automated fashion, smart contracts from BPMN models. The generated smart contracts provide support for multi-step transactions th...

BugWhisperer: Fine-Tuning LLMs for SoC Hardware Vulnerability Detection

The current landscape of system-on-chips SoCs security verification faces challenges due to manual, labor-intensive, and inflexible methodologies. These issues limit the scalability and effectiveness of security protocols, making bug detection at the Register-Transfer Level RTL difficult. This...

Does Johnny Get the Message? Evaluating Cybersecurity Notifications for Everyday Users

Due to the increasing presence of networked devices in everyday life, not only cybersecurity specialists but also end users benefit from security applications such as firewalls, vulnerability scanners, and intrusion detection systems. Recent approaches use large language models LLMs to rewrite...

Privacy-Preserving Inconsistency Measurement

We investigate a new form of privacy-preserving inconsistency measurement for multi-party communication. Intuitively, for two knowledge bases KA, KB of two agents A, B, our results allow to quantitatively assess the degree of inconsistency for KA U KB without having to reveal the actual contents ...

Hunting the Ghost: Towards Automatic Mining of IoT Hidden Services

In this paper, we proposes an automatic firmware analysis tool targeting at finding hidden services that may be potentially harmful to the IoT devices. Our approach uses static analysis and symbolic execution to search and filter services that are transparent to normal users but explicit to...

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...

SimProcess: High Fidelity Simulation of Noisy ICS Physical Processes

Industrial Control Systems ICS manage critical infrastructures like power grids and water treatment plants. Cyberattacks on ICSs can disrupt operations, causing severe economic, environmental, and safety issues. For example, undetected pollution in a water plant can put the lives of thousands at...

Security Benefits and Side Effects of Labeling AI-Generated Images

Generative artificial intelligence is developing rapidly, impacting humans' interaction with information and digital media. It is increasingly used to create deceptively realistic misinformation, so lawmakers have imposed regulations requiring the disclosure of AI-generated content. However, only...

Aurora: Are Android Malware Classifiers Reliable under Distribution Shift?

The performance figures of modern drift-adaptive malware classifiers appear promising, but does this translate to genuine operational reliability? The standard evaluation paradigm primarily focuses on baseline performance metrics, neglecting confidence-error alignment and operational stability...

Accountable, Scalable and DoS-Resilient Secure Vehicular Communication

Paramount to vehicle safety, broadcasted Cooperative Awareness Messages CAMs and Decentralized Environmental Notification Messages DENMs are pseudonymously authenticated for security and privacy protection, with each node needing to have all incoming messages validated within an expiration...

VulBinLLM: LLM-Powered Vulnerability Detection for Stripped Binaries

Recognizing vulnerabilities in stripped binary files presents a significant challenge in software security. Although some progress has been made in generating human-readable information from decompiled binary files with Large Language Models LLMs, effectively and scalably detecting vulnerabilitie...

CADRE: Customizable Assurance of Data Readiness in Privacy-Preserving Federated Learning

Privacy-Preserving Federated Learning PPFL is a decentralized machine learning approach where multiple clients train a model collaboratively. PPFL preserves privacy and security of the client's data by not exchanging it. However, ensuring that data at each client is of high quality and ready for...

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...

Domainator: Detecting and Identifying DNS-Tunneling Malware Using Metadata Sequences

In recent years, malware with tunneling or: covert channel capabilities is on the rise. While malware research led to several methods and innovations, the detection and differentiation of malware solely based on its DNS tunneling features is still in its infancy. Moreover, no work so far has used...

Permissioned LLMs: Enforcing Access Control in Large Language Models

In enterprise settings, organizational data is segregated, siloed and carefully protected by elaborate access control frameworks. These access control structures can completely break down if an LLM fine-tuned on the siloed data serves requests, for downstream tasks, from individuals with disparat...

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space

Large Language Models LLMs, despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understanding these vulnerabilities through black-box jailbreak attacks, which better reflect real-world scenarios, offers critica...

Scrapers Selectively Respect Robots.Txt Directives: Evidence from a Large-Scale Empirical Study

Online data scraping has taken on new dimensions in recent years, as traditional scrapers have been joined by new AI-specific bots. To counteract unwanted scraping, many sites use tools like the Robots Exclusion Protocol REP, which places a robots.txt file at the site root to dictate scraper...

Cryptography from Lossy Reductions: Towards OWFs from ETH, and Beyond

One-way functions OWFs form the foundation of modern cryptography, yet their unconditional existence remains a major open question. In this work, we study this question by exploring its relation to lossy reductions, i.e., reductions$R$ for which it holds that $IX;RX \ll n$ for all distributions$X...

Lazarus Group Targets Crypto-Wallets and Financial Data While Employing New Tradecrafts

This report presents a comprehensive analysis of a malicious software sample, detailing its architecture, behavioral characteristics, and underlying intent. Through static and dynamic examination, the malware core functionalities, including persistence mechanisms, command-and-control communicatio...

System Prompt Extraction Attacks and Defenses in Large Language Models

The system prompt in Large Language Models LLMs plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become an emerging attack target. Recent studies have shown that...

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...

Transformers in Protein: a Survey

As protein informatics advances rapidly, the demand for enhanced predictive accuracy, structural analysis, and functional understanding has intensified. Transformer models, as powerful deep learning architectures, have demonstrated unprecedented potential in addressing diverse challenges across...

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...