相关论文: Exploiting Class Probabilities for Black-box Sente…

Prompt-based classifiers are an attractive approach for zero-shot classification. However, the precise choice of the prompt template and label words can largely influence performance, with semantically equivalent settings often showing…

We present a novel approach for attacking black-box large language models (LLMs) by exploiting their ability to express confidence in natural language. Existing black-box attacks require either access to continuous model outputs like logits…

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…

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

Deep learning models are susceptible to adversarial examples that have imperceptible perturbations in the original input, resulting in adversarial attacks against these models. Analysis of these attacks on the state of the art transformers…

We propose a novel genetic-algorithm technique that generates black-box adversarial examples which successfully fool neural network based text classifiers. We perform a genetic search with multi-objective optimization guided by deep…

Current large language models (LLM) provide a strong foundation for large-scale user-oriented natural language tasks. Many users can easily inject adversarial text or instructions through the user interface, thus causing LLM model security…

Black-box adversarial attacks have demonstrated strong potential to compromise machine learning models by iteratively querying the target model or leveraging transferability from a local surrogate model. Recently, such attacks can be…

The success of deep learning research has catapulted deep models into production systems that our society is becoming increasingly dependent on, especially in the image and video domains. However, recent work has shown that these largely…

Automatic grading models are valued for the time and effort saved during the instruction of large student bodies. Especially with the increasing digitization of education and interest in large-scale standardized testing, the popularity of…

While modern day web applications aim to create impact at the civilization level, they have become vulnerable to adversarial activity, where the next cyber-attack can take any shape and can originate from anywhere. The increasing scale and…

Many classification problems require decisions among a large number of competing classes. These tasks, however, are not handled well by general purpose learning methods and are usually addressed in an ad-hoc fashion. We suggest a general…

We introduce a simple yet efficient sentence-level attack on black-box toxicity detector models. By adding several positive words or sentences to the end of a hateful message, we are able to change the prediction of a neural network and…

Adversarial attacks have become a major threat for machine learning applications. There is a growing interest in studying these attacks in the audio domain, e.g, speech and speaker recognition; and find defenses against them. In this work,…

Social media platforms are deploying machine learning based offensive language classification systems to combat hateful, racist, and other forms of offensive speech at scale. However, despite their real-world deployment, we do not yet…

Recent work has demonstrated the vulnerability of modern text classifiers to universal adversarial attacks, which are input-agnostic sequences of words added to text processed by classifiers. Despite being successful, the word sequences…

Recent research on reinforcement learning (RL) has suggested that trained agents are vulnerable to maliciously crafted adversarial samples. In this work, we show how such samples can be generalised from White-box and Grey-box attacks to a…

Existing black box search methods have achieved high success rate in generating adversarial attacks against NLP models. However, such search methods are inefficient as they do not consider the amount of queries required to generate…

In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedback under a query budget. Due to the limited feedback…

Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the…