相关论文: Adversarial attacks against Fact Extraction and VE…

The ability to deploy neural networks in real-world, safety-critical systems is severely limited by the presence of adversarial examples: slightly perturbed inputs that are misclassified by the network. In recent years, several techniques…

Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they…

As neural networks become the tool of choice to solve an increasing variety of problems in our society, adversarial attacks become critical. The possibility of generating data instances deliberately designed to fool a network's analysis can…

Continual (or "incremental") learning approaches are employed when additional knowledge or tasks need to be learned from subsequent batches or from streaming data. However these approaches are typically adversary agnostic, i.e., they do not…

This paper introduces the task of factual error correction: performing edits to a claim so that the generated rewrite is better supported by evidence. This extends the well-studied task of fact verification by providing a mechanism to…

This paper introduces the task of factual error correction: performing edits to a claim so that the generated rewrite is better supported by evidence. This extends the well-studied task of fact verification by providing a mechanism to…

Adversarial claim rewriting is widely used to test fact-checking systems, but standard metrics fail to capture truth-conditional consistency and often label semantically corrupted rewrites as successful. We introduce AtomEval, a…

In this paper, we highlight our approach for the "Arabic AI Tasks Evaluation (ArAiEval) Shared Task 2023". We present our approaches for task 1-A and task 2-A of the shared task which focus on persuasion technique detection and…

Adversarial attacks and defenses have gained increasing interest on computer vision systems in recent years, but as of today, most investigations are limited to images. However, many artificial intelligence models actually handle…

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In…

Adversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based methods. Current…

Recent work on fact-checking addresses a realistic setting where models incorporate evidence retrieved from the web to decide the veracity of claims. A bottleneck in this pipeline is in retrieving relevant evidence: traditional methods may…

Fact verification aims to automatically probe the veracity of a claim based on several pieces of evidence. Existing works are always engaging in accuracy improvement, let alone explainability, a critical capability of fact verification…

Adversarial attacks reveal important vulnerabilities and flaws of trained models. One potent type of attack are universal adversarial triggers, which are individual n-grams that, when appended to instances of a class under attack, can trick…

We present CFEVER, a Chinese dataset designed for Fact Extraction and VERification. CFEVER comprises 30,012 manually created claims based on content in Chinese Wikipedia. Each claim in CFEVER is labeled as "Supports", "Refutes", or "Not…

Adversarial Examples (AEs) generated by perturbing original training examples are useful in improving the robustness of Deep Learning (DL) based models. Most prior works, generate AEs that are either unconscionable due to lexical errors or…

Various techniques are used in the generation of adversarial examples, including methods such as TextBugger which introduce minor, hardly visible perturbations to words leading to changes in model behaviour. Another class of techniques…

We introduce an adversarial method for producing high-recall explanations of neural text classifier decisions. Building on an existing architecture for extractive explanations via hard attention, we add an adversarial layer which scans the…

Adversarial attacks on machine learning algorithms have been a key deterrent to the adoption of AI in many real-world use cases. They significantly undermine the ability of high-performance neural networks by forcing misclassifications.…

Fake news, misinformation, and unverifiable facts on social media platforms propagate disharmony and affect society, especially when dealing with an epidemic like COVID-19. The task of Fake News Detection aims to tackle the effects of such…