Towards Secure MLOps: Surveying Attacks, Mitigation Strategies, and Research Challenges

The rapid adoption of machine learning ML technologies has driven organizations across diverse sectors to seek efficient and reliable methods to accelerate model development-to-deployment. Machine Learning Operations MLOps has emerged as an integrative approach addressing these requirements by...

When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs

Knowledge files have been widely used in large language model LLM agents, such as GPTs, to improve response quality. However, concerns about the potential leakage of knowledge files have grown significantly. Existing studies demonstrate that adversarial prompts can induce GPTs to leak knowledge...

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...

Dpmm: Differentially Private Marginal Models, a Library for Synthetic Tabular Data Generation

We propose dpmm, an open-source library for synthetic data generation with Differentially Private DP guarantees. It includes three popular marginal models -- PrivBayes, MST, and AIM -- that achieve superior utility and offer richer functionality compared to alternative implementations...

Hush! Protecting Secrets during Model Training: an Indistinguishability Approach

We consider the problem of secret protection, in which a business or organization wishes to train a model on their own data, while attempting to not leak secrets potentially contained in that data via the model. The standard method for training models to avoid memorization of secret information i...

Breaking the Gold Standard: Extracting Forgotten Data under Exact Unlearning in Large Language Models

Large language models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove the influence of specific data from trained models. Of...

Roundcube Webmail 1.6.7 Cross Site Scripting

Roundcube Webmail versions 1.6.7 and below email capture listener and cross site scripting proof of concept exploit...

Looking for Attention: Randomized Attention Test Design for Validator Monitoring in Optimistic Rollups

Optimistic Rollups ORUs significantly enhance blockchain scalability but inherently suffer from the verifier's dilemma, particularly concerning validator attentiveness. Current systems lack mechanisms to proactively ensure validators are diligently monitoring L2 state transitions, creating a...

PatchDEMUX: a Certifiably Robust Framework for Multi-Label Classifiers against Adversarial Patches

Deep learning techniques have enabled vast improvements in computer vision technologies. Nevertheless, these models are vulnerable to adversarial patch attacks which catastrophically impair performance. The physically realizable nature of these attacks calls for certifiable defenses, which featur...

Adversarial Machine Learning for Robust Password Strength Estimation

Passwords remain one of the most common methods for securing sensitive data in the digital age. However, weak password choices continue to pose significant risks to data security and privacy. This study aims to solve the problem by focusing on developing robust password strength estimation models...

Compact and Selective Disclosure for Verifiable Credentials

Self-Sovereign Identity SSI is a novel identity model that empowers individuals with full control over their data, enabling them to choose what information to disclose, with whom, and when. This paradigm is rapidly gaining traction worldwide, supported by numerous initiatives such as the European...

Next Generation Authentication for Data Spaces: an Authentication Flow Based on Grant Negotiation and Authorization Protocol for Verifiable Presentations (GNAP4VP)

Identity verification in Data Spaces is a fundamental aspect of ensuring security and privacy in digital environments. This paper presents an identity verification protocol tailored for shared data environments within Data Spaces. This protocol extends the Grant Negotiation and Authorization...

Shill Bidding Prevention in Decentralized Auctions Using Smart Contracts

In online auctions, fraudulent behaviors such as shill bidding pose significant risks. This paper presents a conceptual framework that applies dynamic, behavior-based penalties to deter auction fraud using blockchain smart contracts. Unlike traditional post-auction detection methods, this approac...

Dynamic Malware Classification of Windows PE Files Using CNNs and Greyscale Images Derived from Runtime API Call Argument Conversion

Malware detection and classification remains a topic of concern for cybersecurity, since it is becoming common for attackers to use advanced obfuscation on their malware to stay undetected. Conventional static analysis is not effective against polymorphic and metamorphic malware as these change...

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents

Voice cloning VC-resistant watermarking is an emerging technique for tracing and preventing unauthorized cloning. Existing methods effectively trace traditional VC models by training them on watermarked audio but fail in zero-shot VC scenarios, where models synthesize audio from an audio prompt...

The Cost of Restaking Vs. Proof-Of-Stake

We compare the efficiency of restaking and Proof-of-Stake PoS protocols in terms of stake requirements. First, we consider the sufficient condition for the restaking graph to be secure. We show that the condition implies that it is always possible to transform such a restaking graph into secure P...

Randextract: a Reference Library to Test and Validate Privacy Amplification Implementations

Quantum cryptographic protocols do not rely only on quantum-physical resources, they also require reliable classical communication and computation. In particular, the secrecy of any quantum key distribution protocol critically depends on the correct execution of the privacy amplification step. Th...

Light As Deception: GPT-Driven Natural Relighting against Vision-Language Pre-Training Models

Whitepaper called Light As Deception: GPT-Driven Natural Relighting Against Vision-Language Pre-Training Models...

Adaptive Privacy-Preserving SSD

Data remanence in NAND flash complicates complete deletion on IoT SSDs. We design an adaptive architecture offering four privacy levels PL0-PL3 that select among address, data, and parity deletion techniques. Quantitative analysis balances efficacy, latency, endurance, and cost. Machine-learning...

Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection

The performance of existing audio deepfake detection frameworks degrades when confronted with new deepfake attacks. Rehearsal-based continual learning CL, which updates models using a limited set of old data samples, helps preserve prior knowledge while incorporating new information. However,...

A Human Study of Cognitive Biases in Web Application Security

Cybersecurity training has become a crucial part of computer science education and industrial onboarding. Capture the Flag CTF competitions have emerged as a valuable, gamified approach for developing and refining the skills of cybersecurity and software engineering professionals. However, while...

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...

Data Flows in You: Benchmarking and Improving Static Data-Flow Analysis on Binary Executables

Data-flow analysis is a critical component of security research. Theoretically, accurate data-flow analysis in binary executables is an undecidable problem, due to complexities of binary code. Practically, many binary analysis engines offer some data-flow analysis capability, but we lack...

Verifiable Weighted Secret Sharing

Traditionally, threshold secret sharing TSS schemes assume all parties have equal weight, yet emerging systems like blockchains reveal disparities in party trustworthiness, such as stake or reputation. Weighted Secret Sharing WSS addresses this by assigning varying weights to parties, ensuring...

Asymmetry by Design: Boosting Cyber Defenders with Differential Access to AI

As AI-enabled cyber capabilities become more advanced, we propose "differential access" as a strategy to tilt the cybersecurity balance toward defense by shaping access to these capabilities. We introduce three possible approaches that form a continuum, becoming progressively more restrictive for...

A Reward-Driven Automated Webshell Malicious-Code Generator for Red-Teaming

Whitepaper called A Reward-Driven Automated Webshell Malicious-Code Generator For Red-Teaming...

Chances and Challenges of the Model Context Protocol in Digital Forensics and Incident Response

Large language models hold considerable promise for supporting forensic investigations, but their widespread adoption is hindered by a lack of transparency, explainability, and reproducibility. This paper explores how the emerging Model Context Protocol can address these challenges and support th...

MUSE: Model-Agnostic Tabular Watermarking Via Multi-Sample Selection

We introduce MUSE, a watermarking algorithm for tabular generative models. Previous approaches typically leverage DDIM invertibility to watermark tabular diffusion models, but tabular diffusion models exhibit significantly poorer invertibility compared to other modalities, compromising performanc...

LPASS: Linear Probes As Stepping Stones for Vulnerability Detection Using Compressed LLMs

Large Language Models LLMs are being extensively used for cybersecurity purposes. One of them is the detection of vulnerable codes. For the sake of efficiency and effectiveness, compression and fine-tuning techniques are being developed, respectively. However, they involve spending substantial...

Transaction Proximity: a Graph-Based Approach to Blockchain Fraud Prevention

This paper introduces a fraud-deterrent access validation system for public blockchains, leveraging two complementary concepts: "Transaction Proximity", which measures the distance between wallets in the transaction graph, and "Easily Attainable Identities EAIs", wallets with direct transaction...

So, I Climbed to the Top of the Pyramid of Pain -- Now What?

This paper explores the evolving dynamics of cybersecurity in the age of advanced AI, from the perspective of the introduced Human Layer Kill Chain framework. As traditional attack models like Lockheed Martin's Cyber Kill Chain become inadequate in addressing human vulnerabilities exploited by...

Differentially Private Space-Efficient Algorithms for Counting Distinct Elements in the Turnstile Model

The turnstile continual release model of differential privacy captures scenarios where a privacy-preserving real-time analysis is sought for a dataset evolving through additions and deletions. In typical applications of real-time data analysis, both the length of the stream $T$ and the size of th...

A Tertiary Review on Quantum Cryptography

Quantum computers impose an immense threat to system security. As a countermeasure, new cryptographic classes have been created to prevent these attacks. Technologies such as post-quantum cryptography and quantum cryptography. Quantum cryptography uses the principle of quantum physics to produce...

Hijacking Large Language Models Via Adversarial In-Context Learning

In-context learning ICL has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations demos in the preconditioned prompts. Despite its promising performance, crafted adversarial attacks pose a notable threat to the robustness of...

Digital Forensic Investigation of the ChatGPT Windows Application

The ChatGPT Windows application offers better user interaction in the Windows operating system OS by enhancing productivity and streamlining the workflow of ChatGPT's utilization. However, there are potential misuses associated with this application that require rigorous forensic analysis. This...

Securing AI Agents with Information-Flow Control

As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control IFC to provide security guarantees for AI agents. We present a formal model to reason about t...

Demonstration of Quantum-Secure Communications in a Nuclear Reactor

Quantum key distribution QKD, one of the latest cryptographic techniques, founded on the laws of quantum mechanics rather than mathematical complexity, promises for the first time unconditional secure remote communications. Integrating this technology into the next generation nuclear systems -...

Bayesian Perspective on Memorization and Reconstruction

We introduce a new Bayesian perspective on the concept of data reconstruction, and leverage this viewpoint to propose a new security definition that, in certain settings, provably prevents reconstruction attacks. We use our paradigm to shed new light on one of the most notorious attacks in the...

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

Cautious predictions -- where a machine learning model abstains when uncertain -- are crucial for limiting harmful errors in safety-critical applications. In this work, we identify a novel threat: a dishonest institution can exploit these mechanisms to discriminate or unjustly deny services under...

The End of Universal Lifelong Identifiers: Identity Systems for the AI Era

Many identity systems assign a single, static identifier to an individual for life, reused across domains like healthcare, finance, and education. These Universal Lifelong Identifiers ULIs underpin critical workflows but now pose systemic privacy risks. We take the position that ULIs are...

Falco 0.41.0

Sysdig Falco is a behavioral activity monitoring agent that is open source and comes with native support for containers. Falco lets you define highly granular rules to check for activities involving file and network activity, process execution, IPC, and much more, using a flexible syntax. Falco...

Disrupting Vision-Language Model-Driven Navigation Services Via Adversarial Object Fusion

We present Adversarial Object Fusion AdvOF, a novel attack framework targeting vision-and-language navigation VLN agents in service-oriented environments by generating adversarial 3D objects. While foundational models like Large Language Models LLMs and Vision Language Models VLMs have enhanced...

LLM Agents Should Employ Security Principles

Large Language Model LLM agents show considerable promise for automating complex tasks using contextual reasoning; however, interactions involving multiple agents and the system's susceptibility to prompt injection and other forms of context manipulation introduce new vulnerabilities related to...

HoneySat: a Network-Based Satellite Honeypot Framework

Satellites are the backbone of several mission-critical services, such as GPS that enable our modern society to function. For many years, satellites were assumed to be secure because of their indecipherable architectures and the reliance on security by obscurity. However, technological advancemen...

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models

Model merging for Large Language Models LLMs directly fuses the parameters of different models finetuned on various tasks, creating a unified model for multi-domain tasks. However, due to potential vulnerabilities in models available on open-source platforms, model merging is susceptible to...

SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?

Fine-tuning large language models LLMs for telecom tasks and datasets is a common practice to adapt general-purpose models to the telecom domain. However, little attention has been paid to how this process may compromise model safety. Recent research has shown that even benign fine-tuning can...

Fooling the Watchers: Breaking AIGC Detectors Via Semantic Prompt Attacks

The rise of text-to-image T2I models has enabled the synthesis of photorealistic human portraits, raising serious concerns about identity misuse and the robustness of AIGC detectors. In this work, we propose an automated adversarial prompt generation framework that leverages a grammar tree...

MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits Using Improved Preference Alignment

The model context protocol MCP has been widely adapted as an open standard enabling the seamless integration of generative AI agents. However, recent work has shown the MCP is susceptible to retrieval-based "falsely benign" attacks FBAs, allowing malicious system access and credential theft, but...

An Advanced Cyber-Physical System Security Testbed for Substation Automation

A Cyber-Physical System CPS testbed serves as a powerful platform for testing and validating cyber intrusion detection and mitigation strategies in substations. This study presents the design and development of a CPS testbed that can effectively assess the real-time dynamics of a substation. Cybe...

Joint Data Hiding and Partial Encryption of Compressive Sensed Streams

The paper proposes a method to secure the Compressive Sensing CS streams. It consists in protecting part of the measurements by a secret key and inserting the code into the rest. The secret key is generated via a cryptographically secure pseudo-random number generator CSPRNG and XORed with the...