Related papers: Attacks by Content: Automated Fact-checking is an …
Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…
Language agents increasingly act as web-enabled systems that search, browse, and synthesize information from diverse sources. However, these sources can include unreliable or adversarial content, and the robustness of agents to adversarial…
The gossip-based distributed algorithms are widely used to solve decentralized optimization problems in various multi-agent applications, while they are generally vulnerable to data injection attacks by internal malicious agents as each…
Not everything on the internet is true. This unfortunate fact requires both humans and models to perform complex reasoning about credibility when working with retrieved information. In NLP, this problem has seen little attention. Indeed,…
Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…
News plays a significant role in shaping people's beliefs and opinions. Fake news has always been a problem, which wasn't exposed to the mass public until the past election cycle for the 45th President of the United States. While quite a…
Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…
Training robust deep learning models for down-stream tasks is a critical challenge. Research has shown that down-stream models can be easily fooled with adversarial inputs that look like the training data, but slightly perturbed, in a way…
Large Language Models (LLMs) are increasingly being integrated into the scientific peer-review process, raising new questions about their reliability and resilience to manipulation. In this work, we investigate the potential for hidden…
We introduce 'FactCheck Editor', an advanced text editor designed to automate fact-checking and correct factual inaccuracies. Given the widespread issue of misinformation, often a result of unintentional mistakes by content creators, our…
Language models remain vulnerable to prompt injection attacks despite extensive safety training. We trace this failure to role confusion: models infer the source of text based on how it sounds, not where it actually comes from. A command…
Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions, because of their instruction-following capabilities and…
We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…
Physiological computing uses human physiological data as system inputs in real time. It includes, or significantly overlaps with, brain-computer interfaces, affective computing, adaptive automation, health informatics, and physiological…
Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this…
The technology of Conversational AI has made significant advancements over the last eighteen months. As a consequence, conversational agents are likely to be deployed in the near future that are designed to pursue targeted influence…
There has been considerable recent interest in explainability in AI, especially with black-box machine learning models. As correctly observed by the planning community, when the application at hand is not a single-shot decision or…
Defending computer networks from cyber attack requires timely responses to alerts and threat intelligence. Decisions about how to respond involve coordinating actions across multiple nodes based on imperfect indicators of compromise while…
In this work, we focus on the problem of distinguishing a human written news article from a news article that is created by manipulating entities in a human written news article (e.g., replacing entities with factually incorrect entities).…
Fact-checking is the task of verifying the veracity of claims by assessing their assertions against credible evidence. The vast majority of fact-checking studies focus exclusively on political claims. Very little research explores…