相关论文: Sorry: Ambient Tactical Deception Via Malware-Base…

Socialbots are software-driven user accounts on social platforms, acting autonomously (mimicking human behavior), with the aims to influence the opinions of other users or spread targeted misinformation for particular goals. As socialbots…

Can language models transform inputs to protect text classifiers against adversarial attacks? In this work, we present ATINTER, a model that intercepts and learns to rewrite adversarial inputs to make them non-adversarial for a downstream…

We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model…

In authentication scenarios, applications of practical speaker verification systems usually require a person to read a dynamic authentication text. Previous studies played an audio adversarial example as a digital signal to perform physical…

Cyber deception is one of the key approaches used to mislead attackers by hiding or providing inaccurate system information. There are two main factors limiting the real-world application of existing cyber deception approaches. The first…

Deception is virtually ubiquitous in warfare, and should be a central consideration for military operations research. However, studies of agent behaviour in simulated operations have typically neglected to include explicit models of…

As conspiracy theories gain traction, it has become crucial to research effective intervention strategies that can foster evidence and science-based discussions in conspiracy theory communities online. This study presents a novel framework…

Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the…

Advanced persistent threat (APT) is widely acknowledged to be the most sophisticated and potent class of security threat. APT refers to knowledgeable human attackers that are organized, highly sophisticated and motivated to achieve their…

The performance of artificial intelligence (AI) algorithms in practice depends on the realism and correctness of the data, models, and feedback (labels or rewards) provided to the algorithm. This paper discusses methods for improving the…

Backdoor attacks on reinforcement learning implant a backdoor in a victim agent's policy. Once the victim observes the trigger signal, it will switch to the abnormal mode and fail its task. Most of the attacks assume the adversary can…

Technology is increasingly used -- unintentionally (misinformation) or intentionally (disinformation) -- to spread false information at scale, with potentially broad-reaching societal effects. For example, technology enables increasingly…

Adversarial purification is a successful defense mechanism against adversarial attacks without requiring knowledge of the form of the incoming attack. Generally, adversarial purification aims to remove the adversarial perturbations…

Augmented Reality (AR) is a powerful perceptual technology that can alter what users see, hear, feel, and experience throughout their daily lives. When combined with the speed and flexibility of context-aware generative AI, the power is…

This article introduces a framework that is meant to assist in mitigating societal risks that software can pose. Concretely, this encompasses facets of software doping as well as unfairness and discrimination in high-risk decision-making…

Automated soft moderation systems are unable to ascertain if a post supports or refutes a false claim, resulting in a large number of contextual false positives. This limits their effectiveness, for example undermining trust in health…

Visual modifications to text are often used to obfuscate offensive comments in social media (e.g., "!d10t") or as a writing style ("1337" in "leet speak"), among other scenarios. We consider this as a new type of adversarial attack in NLP,…

Large language model (LLM) agents are rapidly becoming trusted copilots in high-stakes domains like software development and healthcare. However, this deepening trust introduces a novel attack surface: Agent-Mediated Deception (AMD), where…

Current approaches to addressing deceptive design largely focus on visible interface manipulations, commonly referred to as "dark patterns". With the rise of generative AI, deception is becoming more difficult to spot and easier to live…

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface,…