Related papers: Don't Lie to Me: Avoiding Malicious Explanations w…
How to detect and mitigate deceptive AI systems is an open problem for the field of safe and trustworthy AI. We analyse two algorithms for mitigating deception: The first is based on the path-specific objectives framework where paths in the…
Artificial intelligence (AI) comes with great opportunities but can also pose significant risks. Automatically generated explanations for decisions can increase transparency and foster trust, especially for systems based on automated…
In many contexts, lying -- the use of verbal falsehoods to deceive -- is harmful. While lying has traditionally been a human affair, AI systems that make sophisticated verbal statements are becoming increasingly prevalent. This raises the…
Large language models (LLMs) can "lie", which we define as outputting false statements despite "knowing" the truth in a demonstrable sense. LLMs might "lie", for example, when instructed to output misinformation. Here, we develop a simple…
In this work we present a formal theoretical framework for assessing and analyzing two classes of malevolent action towards generic Artificial Intelligence (AI) systems. Our results apply to general multi-class classifiers that map from an…
We develop and study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence (AI) systems including deep learning neural networks. In contrast to adversarial data modification,…
As more attention is paid to security in the context of control systems and as attacks occur to real control systems throughout the world, it has become clear that some of the most nefarious attacks are those that evade detection. The term…
Differential privacy is a rigorous privacy condition achieved by randomizing query answers. This paper develops efficient algorithms for answering multiple queries under differential privacy with low error. We pursue this goal by advancing…
The honesty of large language models (LLMs) is a critical alignment challenge, especially as advanced systems with chain-of-thought (CoT) reasoning may strategically deceive humans. Unlike traditional honesty issues on LLMs, which could be…
As ongoing research explores the ability of AI agents to be insider threats and act against company interests, we showcase the abilities of such agents to act against human well being in service of corporate authority. Building on Agentic…
Large language models are known to produce outputs that are plausible but factually incorrect. To prevent people from making erroneous decisions by blindly trusting AI, researchers have explored various ways of communicating factuality…
When AI systems explain their reasoning step-by-step, practitioners often assume these explanations reveal what actually influenced the AI's answer. We tested this assumption by embedding hints into questions and measuring whether models…
Scientific collaborations benefit from collaborative learning of distributed sources, but remain difficult to achieve when data are sensitive. In recent years, privacy preserving techniques have been widely studied to analyze distributed…
Clustering is an unsupervised machine learning methodology where unlabeled elements/objects are grouped together aiming to the construction of well-established clusters that their elements are classified according to their similarity. The…
As conversational AI systems become more realistic and widely deployed, users are increasingly uncertain about whether they are interacting with a human or an AI system. When AI identity is unclear, users may unwittingly share sensitive…
We introduce the concept of deceptive diffusion -- training a generative AI model to produce adversarial images. Whereas a traditional adversarial attack algorithm aims to perturb an existing image to induce a misclassificaton, the…
Over the past decade, side-channels have proven to be significant and practical threats to modern computing systems. Recent attacks have all exploited the underlying shared hardware. While practical, mounting such a complicated attack is…
We investigate how low-quality AI advisors, lacking quality disclosures, can help spread text-based lies while seeming to help people detect lies. Participants in our experiment discern truth from lies by evaluating transcripts from a game…
Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity. If an AI system learned such a deceptive…
Machine Learning (ML) algorithms are used to train computers to perform a variety of complex tasks and improve with experience. Computers learn how to recognize patterns, make unintended decisions, or react to a dynamic environment. Certain…