相关论文: Group-Adaptive Adversarial Learning for Robust Fak…

Ideally, what confuses neural network should be confusing to humans. However, recent experiments have shown that small, imperceptible perturbations can change the network prediction. To address this gap in perception, we propose a novel…

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease a victim's cumulative expected reward by manipulating the victim's observations. Despite the efficiency of previous optimization-based methods for…

Security concerns surrounding text-to-image diffusion models have driven researchers to unlearn inappropriate concepts through fine-tuning. Recent fine-tuning methods typically align the prediction distributions of unsafe prompts with those…

With the rapid development of social media, the wide dissemination of fake news on social media is increasingly threatening both individuals and society. One of the unique challenges for fake news detection on social media is how to detect…

The rise of cyberbullying in social media platforms involving toxic comments has escalated the need for effective ways to monitor and moderate online interactions. Existing solutions of automated toxicity detection systems, are based on a…

Offline reinforcement learning (RL) addresses the challenge of expensive and high-risk data exploration inherent in RL by pre-training policies on vast amounts of offline data, enabling direct deployment or fine-tuning in real-world…

Matching information across image and text modalities is a fundamental challenge for many applications that involve both vision and natural language processing. The objective is to find efficient similarity metrics to compare the similarity…

With social media being a major force in information consumption, accelerated propagation of fake news has presented new challenges for platforms to distinguish between legitimate and fake news. Effective fake news detection is a…

Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The latent embedding…

The field of textual adversarial defenses has gained considerable attention in recent years due to the increasing vulnerability of natural language processing (NLP) models to adversarial attacks, which exploit subtle perturbations in input…

Adversarial training is an approach of increasing the robustness of models to adversarial attacks by including adversarial examples in the training set. One major challenge of producing adversarial examples is to contain sufficient…

Due to various and serious adverse impacts of spreading fake news, it is often known that only people with malicious intent would propagate fake news. However, it is not necessarily true based on social science studies. Distinguishing the…

Recently, anomaly scores have been formulated using reconstruction loss of the adversarially learned generators and/or classification loss of discriminators. Unavailability of anomaly examples in the training data makes optimization of such…

Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. These tasks are formulated as a binary classification of responses given in a dialogue context, and models generally learn to make…

Deepfake technology has raised concerns about the authenticity of digital content, necessitating the development of effective detection methods. However, the widespread availability of deepfakes has given rise to a new challenge in the form…

Text classification methods have been widely investigated as a way to detect content of low credibility: fake news, social media bots, propaganda, etc. Quite accurate models (likely based on deep neural networks) help in moderating public…

Real-world natural language processing systems need to be robust to human adversaries. Collecting examples of human adversaries for training is an effective but expensive solution. On the other hand, training on synthetic attacks with small…

An adversarial attack paradigm explores various scenarios for the vulnerability of deep learning models: minor changes of the input can force a model failure. Most of the state of the art frameworks focus on adversarial attacks for images…

Fake news poses a significant threat to public opinion and social stability in modern society. This study presents a comparative evaluation of BERT-like encoder-only models and autoregressive decoder-only large language models (LLMs) for…

Recommender systems play an important role in modern information and e-commerce applications. While increasing research is dedicated to improving the relevance and diversity of the recommendations, the potential risks of state-of-the-art…