Decoding Deception: Understanding Automatic Speech Recognition Vulnerabilities in Evasion and Poisoning Attacks

Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on white-box attacks with constrained optimizations, and...

Foe for Fraud: Transferable Adversarial Attacks in Credit Card Fraud Detection

Credit card fraud detection CCFD is a critical application of Machine Learning ML in the financial sector, where accurately identifying fraudulent transactions is essential for mitigating financial losses. ML models have demonstrated their effectiveness in fraud detection task, in particular with...

Breaking the Illusion of Security Via Interpretation: Interpretable Vision Transformer Systems under Attack

Vision transformer ViT models, when coupled with interpretation models, are regarded as secure and challenging to deceive, making them well-suited for security-critical domains such as medical applications, autonomous vehicles, drones, and robotics. However, successful attacks on these systems ca...

Pushing the Limits of Safety: a Technical Report on the ATLAS Challenge 2025

Multimodal Large Language Models MLLMs have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and improve their safety, we organized the Adversarial Testing...

QGuard:Question-Based Zero-Shot Guard for Multi-Modal LLM Safety

The recent advancements in Large Language ModelsLLMs have had a significant impact on a wide range of fields, from general domains to specialized areas. However, these advancements have also significantly increased the potential for malicious users to exploit harmful and jailbreak prompts for...

Assessing the Resilience of Automotive Intrusion Detection Systems to Adversarial Manipulation

The security of modern vehicles has become increasingly important, with the controller area network CAN bus serving as a critical communication backbone for various Electronic Control Units ECUs. The absence of robust security measures in CAN, coupled with the increasing connectivity of vehicles,...

Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples

Adversarial detection protects models from adversarial attacks by refusing suspicious test samples. However, current detection methods often suffer from weak generalization: their effectiveness tends to degrade significantly when applied to adversarially trained models rather than naturally train...

Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack

Membership inference attack MIA has become one of the most widely used and effective methods for evaluating the privacy risks of machine learning models. These attacks aim to determine whether a specific sample is part of the model's training set by analyzing the model's output. While traditional...

Tarallo: Evading Behavioral Malware Detectors in the Problem Space

Machine learning algorithms can effectively classify malware through dynamic behavior but are susceptible to adversarial attacks. Existing attacks, however, often fail to find an effective solution in both the feature and problem spaces. This issue arises from not addressing the intrinsic...

CVE-2021-42023

A vulnerability has been identified in ModelSim Simulation All versions, Questa Simulation All versions. The RSA white-box implementation in affected applications insufficiently protects the built-in private keys that are required to decrypt electronic intellectual property IP data in accordance...

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...

Adversarial Suffix Filtering: a Defense Pipeline for LLMs

Large Language Models LLMs are increasingly embedded in autonomous systems and public-facing environments, yet they remain susceptible to jailbreak vulnerabilities that may undermine their security and trustworthiness. Adversarial suffixes are considered to be the current state-of-the-art...

DP-TRAE: a Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protection

In the field of digital security, Reversible Adversarial Examples RAE combine adversarial attacks with reversible data hiding techniques to effectively protect sensitive data and prevent unauthorized analysis by malicious Deep Neural Networks DNNs. However, existing RAE techniques primarily focus...

OET: Optimization-Based Prompt Injection Evaluation Toolkit

Large Language Models LLMs have demonstrated remarkable capabilities in natural language understanding and generation, enabling their widespread adoption across various domains. However, their susceptibility to prompt injection attacks poses significant security risks, as adversarial inputs can...

Quantifying Source Speaker Leakage in One-To-One Voice Conversion

Using a multi-accented corpus of parallel utterances for use with commercial speech devices, we present a case study to show that it is possible to quantify a degree of confidence about a source speaker's identity in the case of one-to-one voice conversion. Following voice conversion using a...

Bypassing Prompt Injection and Jailbreak Detection in LLM Guardrails

Large Language Models LLMs guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection and jailbreak detection systems via traditional character...

Top 10 web application vulnerabilities in 2021–2023

To help companies with navigating the world of web application vulnerabilities and securing their own web applications, the Open Web Application Security Project OWASP online community created the OWASP Top Ten. As we followed their rankings, we noticed that the way we ranked major vulnerabilitie...

PhotoShow 3.0 Remote Code Execution

Exploit Title: PhotoShow 3.0 - Remote Code Execution Date: January 11, 2023 Exploit Author: LSCP Responsible Disclosure Lab Detailed Bug Description: https://lscp.llc/index.php/2021/07/19/how-white-box-hacking-works-remote-code-execution-and-stored-xss-in-photoshow-3-0/ Vendor Homepage:...

Workspace App 2203 LTSR CU2 displays a blank white box after login

Citrix Workspace App displays a blank white box after login. Issue does not happen when testing older versions of Citrix Workspace App such as 1912CU3...

GHSA-C8FJ-4PM8-MP2C Broken Authorization in ZITADEL Actions

Impact Actions, introduced in ZITADEL 1.42.0 on the API and 1.56.0 for Console, is a feature, where users with role ORGOWNER are able to create Javascript Code, which is invoked by the system at certain points during the login. Actions, for example, allow creating authorizations user grants on...