相关论文: EIA: Environmental Injection Attack on Generalist …
Privacy policies of websites are often lengthy and intricate. Privacy assistants assist in simplifying policies and making them more accessible and user friendly. The emergence of generative AI (genAI) offers new opportunities to build…
While location data is extremely valuable for various applications, disclosing it prompts serious threats to individuals' privacy. To limit such concerns, organizations often provide analysts with aggregate time-series that indicate, e.g.,…
Growth in technology has resulted in the large-scale collection and processing of Personally Identifiable Information by organizations that run digital services such as websites, which led to the emergence of new legislation to regulate PII…
We present CAIA, a benchmark exposing a critical blind spot in AI evaluation: the inability of state-of-the-art models to operate in adversarial, high-stakes environments where misinformation is weaponized and errors are irreversible. While…
For over a decade, cybersecurity has relied on human labor scarcity to limit attackers to high-value targets manually or generic automated attacks at scale. Building sophisticated exploits requires deep expertise and manual effort, leading…
Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration. However, the rapid growth of plugins, connectors, and…
When AI agents retrieve and reason over external documents, adversaries can manipulate the data they receive to subvert their behaviour. Previous research has studied indirect prompt injection, where the attacker injects malicious…
The rapid advancement of artificial intelligence (AI) systems suggests that artificial general intelligence (AGI) systems may soon arrive. Many researchers are concerned that AIs and AGIs will harm humans via intentional misuse (AI-misuse)…
AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target…
It is difficult for individuals and organizations to protect personal information without a fundamental understanding of relative privacy risks. By analyzing over 5,000 empirical identity theft and fraud cases, this research identifies…
Embodied Artificial Intelligence (AI) promises to handle edge cases in robotic vehicle systems where data is scarce by using common-sense reasoning grounded in perception and action to generalize beyond training distributions and adapt to…
AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss. The only known robust defense is architectural isolation that strictly separates trusted task…
Despite the growing integration of retrieval-enabled AI agents into society, their safety and ethical behavior remain inadequately understood. In particular, the integration of LLMs and AI agents with external information sources and…
Distributed Artificial Intelligence (DAI) is regarded as one of the most promising techniques to provide intelligent services under strict privacy protection regulations for multiple clients. By applying DAI, training on raw data is carried…
Web agents can autonomously complete online tasks by interacting with websites, but their exposure to open web environments makes them vulnerable to prompt injection attacks embedded in HTML content or visual interfaces. Existing guard…
Artificial Intelligence (AI) has witnessed major growth and integration across various domains. As AI systems become increasingly prevalent, they also become targets for threat actors to manipulate their functionality for malicious…
With the introduction of regulations related to the ``right to be forgotten", federated learning (FL) is facing new privacy compliance challenges. To address these challenges, researchers have proposed federated unlearning (FU). However,…
In this work, we introduce PII-Scope, a comprehensive benchmark designed to evaluate state-of-the-art methodologies for PII extraction attacks targeting LLMs across diverse threat settings. Our study provides a deeper understanding of these…
This chapter introduces the concept of Autonomous Intelligent Cyber-defense Agents (AICAs), and briefly explains the importance of this field and the motivation for its emergence. AICA is a software agent that resides on a system, and is…
The rapid adoption of deep learning in sensitive domains has brought tremendous benefits. However, this widespread adoption has also given rise to serious vulnerabilities, particularly model inversion (MI) attacks, posing a significant…