Related papers: SEA: Shareable and Explainable Attribution for Que…

Malicious server (MS) attacks have enabled the scaling of data stealing in federated learning to large batch sizes and secure aggregation, settings previously considered private. However, many concerns regarding the client-side…

As large language models (LLMs) continue to advance in capability and influence, ensuring their security and preventing harmful outputs has become crucial. A promising approach to address these concerns involves training models to…

Social Explainable AI (SAI) is a new direction in artificial intelligence that emphasises decentralisation, transparency, social context, and focus on the human users. SAI research is still at an early stage. Consequently, it concentrates…

Modern machine learning (ML) ecosystems offer a surging number of ML frameworks and code repositories that can greatly facilitate the development of ML models. Today, even ordinary data holders who are not ML experts can apply off-the-shelf…

In this paper, we present a generic, query-efficient black-box attack against API call-based machine learning malware classifiers. We generate adversarial examples by modifying the malware's API call sequences and non-sequential features…

Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), and Agent Memory Retrieval. Recent studies have demonstrated…

Model extraction emerges as a critical security threat with attack vectors exploiting both algorithmic and implementation-based approaches. The main goal of an attacker is to steal as much information as possible about a protected victim…

Machine learning is a field of artificial intelligence (AI) that is becoming essential for several critical systems, making it a good target for threat actors. Threat actors exploit different Tactics, Techniques, and Procedures (TTPs)…

Federated learning (FL) is a popular approach to facilitate privacy-aware machine learning since it allows multiple clients to collaboratively train a global model without granting others access to their private data. It is, however, known…

Model extraction (ME) attacks represent one major threat to Machine-Learning-as-a-Service (MLaaS) platforms by ``stealing'' the functionality of confidential machine-learning models through querying black-box APIs. Over seven years have…

In this article, we propose the Artificial Intelligence Security Taxonomy to systematize the knowledge of threats, vulnerabilities, and security controls of machine-learning-based (ML-based) systems. We first classify the damage caused by…

Split Learning (SL) has emerged as a promising paradigm for distributed deep learning, allowing resource-constrained clients to offload portions of their model computation to servers while maintaining collaborative learning. However, recent…

Machine learning (ML) models deployed in many safety- and business-critical systems are vulnerable to exploitation through adversarial examples. A large body of academic research has thoroughly explored the causes of these blind spots,…

Among all privacy attacks against Machine Learning (ML), membership inference attacks (MIA) attracted the most attention. In these attacks, the attacker is given an ML model and a data point, and they must infer whether the data point was…

We introduce Advertisement Embedding Attacks (AEA), a new class of LLM security threats that stealthily inject promotional or malicious content into model outputs and AI agents. AEA operate through two low-cost vectors: (1) hijacking…

Deep neural networks for image classification remain vulnerable to adversarial examples -- small, imperceptible perturbations that induce misclassifications. In black-box settings, where only the final prediction is accessible, crafting…

Machine-learning-as-a-service (MLaaS) has attracted millions of users to their splendid large-scale models. Although published as black-box APIs, the valuable models behind these services are still vulnerable to imitation attacks. Recently,…

Large language models (LLMs) used across enterprises often use proprietary models and operate on sensitive inputs and data. The wide range of attack vectors identified in prior research - targeting various software and hardware components…

As machine learning (ML) systems expand in both scale and functionality, the security landscape has become increasingly complex, with a proliferation of attacks and defenses. However, existing studies largely treat these threats in…

Large language models (LLMs) possess impressive linguistic capabilities but often fail to faithfully retain factual knowledge, leading to hallucinations and unreliable outputs. Understanding LLMs' knowledge deficiencies by exhaustively…