Subverting AIOps Systems Through Poisoned Input Data

In this input integrity attack against an AI system, researchers were able to fool AIOps tools: AIOps refers to the use of LLM-based agents to gather and analyze application telemetry, including system logs, performance metrics, traces, and alerts, to detect problems and then suggest or carry out...

Aura-CAPTCHA: a Reinforcement Learning and GAN-Enhanced Multi-Modal CAPTCHA System

Aura-CAPTCHA was developed as a multi-modal CAPTCHA system to address vulnerabilities in traditional methods that are increasingly bypassed by AI technologies, such as Optical Character Recognition OCR and adversarial image processing. The design integrated Generative Adversarial Networks GANs fo...

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...

Enhancing Targeted Adversarial Attacks on Large Vision-Language Models through Intermediate Projector Guidance

Targeted adversarial attacks are essential for proactively identifying security flaws in Vision-Language Models before real-world deployment. However, current methods perturb images to maximize global similarity with the target text or reference image at the encoder level, collapsing rich visual...

Adversarial Attacks on VQA-NLE: Exposing and Alleviating Inconsistencies in Visual Question Answering Explanations

Natural language explanations in visual question answering VQA-NLE aim to make black-box models more transparent by elucidating their decision-making processes. However, we find that existing VQA-NLE systems can produce inconsistent explanations and reach conclusions without genuinely understandi...

Mitigating Jailbreaks with Intent-Aware LLMs

Despite extensive safety-tuning, large language models LLMs remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose Intent-FT, a simple and lightweight fine-tuning approach that...

Demystifying the Role of Rule-Based Detection in AI Systems for Windows Malware Detection

Malware detection increasingly relies on AI systems that integrate signature-based detection with machine learning. However, these components are typically developed and combined in isolation, missing opportunities to reduce data complexity and strengthen defenses against adversarial EXEmples,...

MetaGuardian: Enhancing Voice Assistant Security through Advanced Acoustic Metamaterials

We present MetaGuardian, a voice assistant VA protection system based on acoustic metamaterials. MetaGuardian can be directly integrated into the enclosures of various smart devices, effectively defending against inaudible, adversarial and laser attacks without relying on additional software...

Exploring Cross-Stage Adversarial Transferability in Class-Incremental Continual Learning

Class-incremental continual learning addresses catastrophic forgetting by enabling classification models to preserve knowledge of previously learned classes while acquiring new ones. However, the vulnerability of the models against adversarial attacks during this process has not been investigated...

Evasive Ransomware Attacks Using Low-Level Behavioral Adversarial Examples

Protecting state-of-the-art AI-based cybersecurity defense systems from cyber attacks is crucial. Attackers create adversarial examples by adding small changes i.e., perturbations to the attack features to evade or fool the deep learning model. This paper introduces the concept of low-level...

Generative AI for Critical Infrastructure in Smart Grids: a Unified Framework for Synthetic Data Generation and Anomaly Detection

In digital substations, security events pose significant challenges to the sustained operation of power systems. To mitigate these challenges, the implementation of robust defense strategies is critically important. A thorough process of anomaly identification and detection in information and...

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection

Ensuring LLM alignment is critical to information security as AI models become increasingly widespread and integrated in society. Unfortunately, many defenses against adversarial attacks and jailbreaking on LLMs cannot adapt quickly to new attacks, degrade model responses to benign prompts, or...

Who'S the Evil Twin? Differential Auditing for Undesired Behavior

Detecting hidden behaviors in neural networks poses a significant challenge due to minimal prior knowledge and potential adversarial obfuscation. We explore this problem by framing detection as an adversarial game between two teams: the red team trains two similar models, one trained solely on...

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs

Large language models LLMs demonstrate impressive capabilities in various language tasks but are susceptible to jailbreak attacks that circumvent their safety alignments. This paper introduces Latent Fusion Jailbreak LFJ, a representation-based attack that interpolates hidden states from harmful...

AuthPrint: Fingerprinting Generative Models against Malicious Model Providers

Generative models are increasingly adopted in high-stakes domains, yet current deployments offer no mechanisms to verify the origin of model outputs. We address this gap by extending model fingerprinting techniques beyond the traditional collaborative setting to one where the model provider may a...

From Split to Share: Private Inference with Distributed Feature Sharing

Cloud-based Machine Learning as a Service MLaaS raises serious privacy concerns when handling sensitive client data. Existing Private Inference PI methods face a fundamental trade-off between privacy and efficiency: cryptographic approaches offer strong protection but incur high computational...

When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

As large language models become increasingly integrated into daily life, audio has emerged as a key interface for human-AI interaction. However, this convenience also introduces new vulnerabilities, making audio a potential attack surface for adversaries. Our research introduces WhisperInject, a...

A Survey on Data Security in Large Language Models

Large Language Models LLMs, now a foundation in advancing natural language processing, power applications such as text generation, machine translation, and conversational systems. Despite their transformative potential, these models inherently rely on massive amounts of training data, often...

DINA: a Dual Defense Framework against Internal Noise and External Attacks in Natural Language Processing

As large language models LLMs and generative AI become increasingly integrated into customer service and moderation applications, adversarial threats emerge from both external manipulations and internal label corruption. In this work, we identify and systematically address these dual adversarial...

Beyond Vulnerabilities: a Survey of Adversarial Attacks As Both Threats and Defenses in Computer Vision Systems

Adversarial attacks against computer vision systems have emerged as a critical research area that challenges the fundamental assumptions about neural network robustness and security. This comprehensive survey examines the evolving landscape of adversarial techniques, revealing their dual nature a...