Vulnerability of Transfer-Learned Neural Networks to Data Reconstruction Attacks in Small-Data Regime

Training data reconstruction attacks enable adversaries to recover portions of a released model's training data. We consider the attacks where a reconstructor neural network learns to invert the random mapping between training data and model weights. Prior work has shown that an informed adversar...

Relational Hoare Logic for Realistically Modelled Machine Code

Many security- and performance-critical domains, such as cryptography, rely on low-level verification to minimize the trusted computing surface and allow code to be written directly in assembly. However, verifying assembly code against a realistic machine model is a challenging task. Furthermore,...

The Hidden Dangers of Outdated Software: a Cyber Security Perspective

Outdated software remains a potent and underappreciated menace in 2025's cybersecurity environment, exposing systems to a broad array of threats, including ransomware, data breaches, and operational outages that can have devastating and far-reaching impacts. This essay explores the unseen threats...

Evaluating the Efficacy of LLM Safety Solutions : the Palit Benchmark Dataset

Large Language Models LLMs are increasingly integrated into critical systems in industries like healthcare and finance. Users can often submit queries to LLM-enabled chatbots, some of which can enrich responses with information retrieved from internal databases storing sensitive data. This gives...

Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the Edge

Artificial neural network pruning is a method in which artificial neural network sizes can be reduced while attempting to preserve the predicting capabilities of the network. This is done to make the model smaller or faster during inference time. In this work we analyze the ability of a selection...

Lessons from Defending Gemini against Indirect Prompt Injections

Gemini is increasingly used to perform tasks on behalf of users, where function-calling and tool-use capabilities enable the model to access user data. Some tools, however, require access to untrusted data introducing risk. Adversaries can embed malicious instructions in untrusted data which caus...

Streamlining HTTP Flooding Attack Detection through Incremental Feature Selection

Applications over the Web primarily rely on the HTTP protocol to transmit web pages to and from systems. There are a variety of application layer protocols, but among all, HTTP is the most targeted because of its versatility and ease of integration with online services. The attackers leverage the...

Covert Attacks on Machine Learning Training in Passively Secure MPC

Secure multiparty computation MPC allows data owners to train machine learning models on combined data while keeping the underlying training data private. The MPC threat model either considers an adversary who passively corrupts some parties without affecting their overall behavior, or an adversa...

CRYPTONITE: Scalable Accelerator Design for Cryptographic Primitives and Algorithms

Cryptographic primitives, consisting of repetitive operations with different inputs, are typically implemented using straight-line C code due to traditional execution on CPUs. Computing these primitives is necessary for secure communication; thus, dedicated hardware accelerators are required in...

Traceable Black-Box Watermarks for Federated Learning

Whitepaper called Traceable Black-Box Watermarks For Federated Learning...

Shielding Latent Face Representations from Privacy Attacks

In today's data-driven analytics landscape, deep learning has become a powerful tool, with latent representations, known as embeddings, playing a central role in several applications. In the face analytics domain, such embeddings are commonly used for biometric recognition e.g., face...

A Systematic Review and Taxonomy for Privacy Breach Classification: Trends, Gaps, and Future Directions

In response to the rising frequency and complexity of data breaches and evolving global privacy regulations, this study presents a comprehensive examination of academic literature on the classification of privacy breaches and violations between 2010-2024. Through a systematic literature review, a...

BeamClean: Language Aware Embedding Reconstruction

In this work, we consider an inversion attack on the obfuscated input embeddings sent to a language model on a server, where the adversary has no access to the language model or the obfuscation mechanism and sees only the obfuscated embeddings along with the model's embedding table. We propose...

QUT-DV25: a Dataset for Dynamic Analysis of Next-Gen Software Supply Chain Attacks

Securing software supply chains is a growing challenge due to the inadequacy of existing datasets in capturing the complexity of next-gen attacks, such as multiphase malware execution, remote access activation, and dynamic payload generation. Existing datasets, which rely on metadata inspection a...

Fragments to Facts: Partial-Information Fragment Inference from LLMs

Large language models LLMs can leak sensitive training data through memorization and membership inference attacks. Prior work has primarily focused on strong adversarial assumptions, including attacker access to entire samples or long, ordered prefixes, leaving open the question of how vulnerable...

Provable Execution in Real-Time Embedded Systems

Embedded devices are increasingly ubiquitous and vital, often supporting safety-critical functions. However, due to strict cost and energy constraints, they are typically implemented with Micro-Controller Units MCUs that lack advanced architectural security features. Within this space, recent...

Quantum Opacity, Classical Clarity: a Hybrid Approach to Quantum Circuit Obfuscation

Quantum computing leverages quantum mechanics to achieve computational advantages over classical hardware, but the use of third-party quantum compilers in the Noisy Intermediate-Scale Quantum NISQ era introduces risks of intellectual property IP exposure. We address this by proposing a novel...

Information-Theoretically Secure Quantum Timestamping with One-Time Universal Hashing

Accurate and tamper-resistant timestamps are essential for applications demanding verifiable chronological ordering, such as legal documentation and digital intellectual property protection. Classical timestamp protocols rely on computational assumptions for security, rendering them vulnerable to...

VulCPE: Context-Aware Cybersecurity Vulnerability Retrieval and Management

The dynamic landscape of cybersecurity demands precise and scalable solutions for vulnerability management in heterogeneous systems, where configuration-specific vulnerabilities are often misidentified due to inconsistent data in databases like the National Vulnerability Database NVD. Inaccurate...

Writing a Good Security Paper for ISSCC (2025)

Security is increasingly more important in designing chips and systems based on them, and the International Solid-State Circuits Conference ISSCC, the leading conference for presenting advances in solid-state circuits and semiconductor technology, is committed to hardware security by establishing...

Malware Families Discovery Via Open-Set Recognition on Android Manifest Permissions

Malware are malicious programs that are grouped into families based on their penetration technique, source code, and other characteristics. Classifying malware programs into their respective families is essential for building effective defenses against cyber threats. Machine learning models have ...

Testing Access-Control Configuration Changes for Web Applications

Access-control misconfigurations are among the main causes of today's data breaches in web applications. However, few techniques are available to support automatic and systematic testing for access-control changes and detecting risky changes to prevent severe consequences. As a result, those...

Outsourced Privacy-Preserving Feature Selection Based on Fully Homomorphic Encryption

Feature selection is a technique that extracts a meaningful subset from a set of features in training data. When the training data is large-scale, appropriate feature selection enables the removal of redundant features, which can improve generalization performance, accelerate the training process...

Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?

Low rank adaptation LoRA has emerged as a prominent technique for fine-tuning large language models LLMs thanks to its superb efficiency gains over previous methods. While extensive studies have examined the performance and structural properties of LoRA, its behavior upon training-time attacks...

ACE: Confidential Computing for Embedded RISC-V Systems

Confidential computing plays an important role in isolating sensitive applications from the vast amount of untrusted code commonly found in the modern cloud. We argue that it can also be leveraged to build safer and more secure mission-critical embedded systems. In this paper, we introduce the...

The Hidden Dangers of Browsing AI Agents

Autonomous browsing agents powered by large language models LLMs are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface. This paper presents a comprehensive security evaluation of...

Network-Wide Quantum Key Distribution with Onion Routing Relay (Conference Version)

The advancement of quantum computing threatens classical cryptographic methods, necessitating the development of secure quantum key distribution QKD solutions for QKD Networks QKDN. In this paper, a novel key distribution protocol, Onion Routing Relay ORR, that integrates onion routing OR with...

FlowPure: Continuous Normalizing Flows for Adversarial Purification

Despite significant advancements in the area, adversarial robustness remains a critical challenge in systems employing machine learning models. The removal of adversarial perturbations at inference time, known as adversarial purification, has emerged as a promising defense strategy. To achieve...

Recommender Systems for Democracy: toward Adversarial Robustness in Voting Advice Applications

Voting advice applications VAAs help millions of voters understand which political parties or candidates best align with their views. This paper explores the potential risks these applications pose to the democratic process when targeted by adversarial entities. In particular, we expose 11...

DynaNoise: Dynamic Probabilistic Noise Injection for Defending against Membership Inference Attacks

Membership Inference Attacks MIAs pose a significant risk to the privacy of training datasets by exploiting subtle differences in model outputs to determine whether a particular data sample was used during training. These attacks can compromise sensitive information, especially in domains such as...

RAR: Setting Knowledge Tripwires for Retrieval Augmented Rejection

Content moderation for large language models LLMs remains a significant challenge, requiring flexible and adaptable solutions that can quickly respond to emerging threats. This paper introduces Retrieval Augmented Rejection RAR, a novel approach that leverages a retrieval-augmented generation RAG...

MorphMark: Flexible Adaptive Watermarking for Large Language Models

Watermarking by altering token sampling probabilities based on red-green list is a promising method for tracing the origin of text generated by large language models LLMs. However, existing watermark methods often struggle with a fundamental dilemma: improving watermark effectiveness the...

Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction

LLM-based autonomous agents possess capabilities such as reasoning, tool invocation, and environment interaction, enabling the execution of complex multi-step tasks. The internal reasoning process, i.e., thought, of behavioral trajectory significantly influences tool usage and subsequent actions...

MCP Guardian: a Security-First Layer for Safeguarding MCP-Based AI System

As Agentic AI gain mainstream adoption, the industry invests heavily in model capabilities, achieving rapid leaps in reasoning and quality. However, these systems remain largely confined to data silos, and each new integration requires custom logic that is difficult to scale. The Model Context...

ArcGIS Insecure OAuth 2.0 Implementation

The ArcGIS clientcredentials OAuth 2.0 API implementation does not adhere to the RFC/standards; This hidden known and by-design, but undocumented functionality enables a requester referred to as client in RFC 6749 to request an, undocumented, custom token expiration from ArcGIS referred to as...

WordPress Eventin 4.0.26 Privilege Escalation

WordPress Eventin plugin versions 4.0.26 and below suffers from an unauthenticated privilege escalation vulnerability due to a missing authorization check in the importitems function...

Network-Wide Quantum Key Distribution with Onion Routing Relay

The advancement of quantum computing threatens classical cryptographic methods, necessitating the development of secure quantum key distribution QKD solutions for QKD Networks QKDN. In this paper, a novel key distribution protocol, Onion Routing Relay ORR, that integrates onion routing OR with...

An Automated Blackbox Noncompliance Checker for QUIC Server Implementations

We develop QUICtester, an automated approach for uncovering non-compliant behaviors in the ratified QUIC protocol implementations RFC 9000/9001. QUICtester leverages active automata learning to abstract the behavior of a QUIC implementation into a finite state machine FSM representation. Unlike...

Multiple Proposer Transaction Fee Mechanism Design: Robust Incentives against Censorship and Bribery

Censorship resistance is one of the core value proposition of blockchains. A recurring design pattern aimed at providing censorship resistance is enabling multiple proposers to contribute inputs into block construction. Notably, Fork-Choice Enforced Inclusion Lists FOCIL is proposed to be include...

FLTG: Byzantine-Robust Federated Learning Via Angle-Based Defense and Non-IID-Aware Weighting

Byzantine attacks during model aggregation in Federated Learning FL threaten training integrity by manipulating malicious clients' updates. Existing methods struggle with limited robustness under high malicious client ratios and sensitivity to non-i.i.d. data, leading to degraded accuracy. To...

DeFeed: Secure Decentralized Cross-Contract Data Feed in Web 3.0 for Connected Autonomous Vehicles

Smart contracts have been a topic of interest in blockchain research and are a key enabling technology for Connected Autonomous Vehicles CAVs in the era of Web 3.0. These contracts enable trustless interactions without the need for intermediaries, as they operate based on predefined rules encoded...

Security Degradation in Iterative AI Code Generation -- a Systematic Analysis of the Paradox

The rapid adoption of Large Language ModelsLLMs for code generation has transformed software development, yet little attention has been given to how security vulnerabilities evolve through iterative LLM feedback. This paper analyzes security degradation in AI-generated code through a controlled...

Apple Security Advisory 05-12-2025-2

Apple Security Advisory 05-12-2025-2 - iPadOS 17.7.7 addresses code execution, double free, information leakage, integer overflow, out of bounds read, spoofing, and use-after-free vulnerabilities...

Apple Security Advisory 05-12-2025-1

Apple Security Advisory 05-12-2025-1 - iOS 18.5 and iPadOS 18.5 addresses code execution, double free, integer overflow, out of bounds read, spoofing, and use-after-free vulnerabilities...

An Alignment between the CRA'S Essential Requirements and the ATT&CK'S Mitigations

The paper presents an alignment evaluation between the mitigations present in the MITRE's ATT&CK framework and the essential cyber security requirements of the recently introduced Cyber Resilience Act CRA in the European Union. In overall, the two align well with each other. With respect to the...

Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy

Federated Learning with client-level differential privacy DP provides a promising framework for collaboratively training models while rigorously protecting clients' privacy. However, classic approaches like DP-FedAvg struggle when clients have heterogeneous privacy requirements, as they must...

When Mitigations Backfire: Timing Channel Attacks and Defense for PRAC-Based RowHammer Mitigations

Per Row Activation Counting PRAC has emerged as a robust framework for mitigating RowHammer RH vulnerabilities in modern DRAM systems. However, we uncover a critical vulnerability: a timing channel introduced by the Alert Back-Off ABO protocol and Refresh Management RFM commands. We present...

Apple Security Advisory 05-12-2025-9

Apple Security Advisory 05-12-2025-9 - Safari 18.5 addresses various issues that could lead to memory corruption...

HChain 4.0: a Secure and Scalable Permissioned Blockchain for EHR Management in Smart Healthcare

The growing utilization of Internet of Medical Things IoMT devices, including smartwatches and wearable medical devices, has facilitated real-time health monitoring and data analysis to enhance healthcare outcomes. These gadgets necessitate improved security measures to safeguard sensitive health...

Apple Security Advisory 05-12-2025-3

Apple Security Advisory 05-12-2025-3 - macOS Sequoia 15.5 addresses bypass, code execution, double free, information leakage, integer overflow, out of bounds read, and use-after-free vulnerabilities...