Related papers: EIA: Environmental Injection Attack on Generalist …
Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), only check if a given data point \textit{exactly} matches a…
The need for secure and private Artificial Intelligence (AI) and Machine Learning (ML) on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an…
Internet users have been exposing an increasing amount of Personally Identifiable Information (PII) on social media. Such exposed PII can cause severe losses to the users, and informing users of their PII exposure is crucial to raise their…
This paper investigates the critical issue of data poisoning attacks on AI models, a growing concern in the ever-evolving landscape of artificial intelligence and cybersecurity. As advanced technology systems become increasingly prevalent…
The ability of machines to comprehend and produce language that is similar to that of humans has revolutionized sectors like customer service, healthcare, and finance thanks to the quick advances in Natural Language Processing (NLP), which…
Artificial intelligence (AI) models introduce privacy vulnerabilities to systems. These vulnerabilities may impact model owners or system users; they exist during model development, deployment, and inference phases, and threats can be…
Membership inference attacks (MIAs) against machine learning (ML) models aim to determine whether a given data point was part of the model training data. These attacks may pose significant privacy risks to individuals whose sensitive data…
This study investigates malicious AI Assistants' manipulative traits and whether the behaviours of malicious AI Assistants can be detected when interacting with human-like simulated users in various decision-making contexts. We also examine…
As autonomous agents become more powerful and widely used, it is becoming increasingly important to ensure they behave safely and stay aligned with system goals, especially in multi-agent settings. Current systems often rely on agents…
While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can…
In recent years, machine learning models, especially deep neural networks, have been widely used for classification tasks in the security domain. However, these models have been shown to be vulnerable to adversarial manipulation: small…
Federated Learning (FL) has emerged as a promising privacy-preserving collaborative model training paradigm without sharing raw data. However, recent studies have revealed that private information can still be leaked through shared gradient…
Interference alignment (IA) has attracted enormous research interest as it achieves optimal capacity scaling with respect to signal to noise ratio on interference networks. IA has also recently emerged as an effective tool in engineering…
This technical report investigates the integration of generative AI (GenAI), specifically ChatGPT, into the practice of ethical hacking through a comprehensive experimental study and conceptual analysis. Conducted in a controlled virtual…
This systematic literature review investigates perceptions, concerns, and expectations of young digital citizens regarding privacy in artificial intelligence (AI) systems, focusing on social media platforms, educational technology, gaming…
Training machine learning models on privacy-sensitive data has become a popular practice, driving innovation in ever-expanding fields. This has opened the door to new attacks that can have serious privacy implications. One such attack, the…
Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own…
Recent works have identified a gap between research and practice in artificial intelligence security: threats studied in academia do not always reflect the practical use and security risks of AI. For example, while models are often studied…
AI agents aim to solve complex tasks by combining text-based reasoning with external tool calls. Unfortunately, AI agents are vulnerable to prompt injection attacks where data returned by external tools hijacks the agent to execute…
We present a comprehensive analysis of privacy attacks and countermeasures in data-driven systems. We systematically categorize attacks targeting three domains: anonymous data (linkage and structural attacks), statistical aggregates…