Related papers: Adversarial Evasion Attack Efficiency against Larg…

There has been recently a growing interest in studying adversarial examples on natural language models in the black-box setting. These methods attack natural language classifiers by perturbing certain important words until the classifier…

Large language models (LLMs) excel in many diverse applications beyond language generation, e.g., translation, summarization, and sentiment analysis. One intriguing application is in text classification. This becomes pertinent in the realm…

Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Large Language Models (LLMs) are powerful zero-shot assessors used in real-world situations such as assessing written exams and benchmarking systems. Despite these critical applications, no existing work has analyzed the vulnerability of…

The widespread use of Vision Language Models (VLMs, e.g. CLIP) has raised concerns about their vulnerability to sophisticated and imperceptible adversarial attacks. These attacks could compromise model performance and system security in…

Previous research on testing the vulnerabilities in Large Language Models (LLMs) using adversarial attacks has primarily focused on nonsensical prompt injections, which are easily detected upon manual or automated review (e.g., via byte…

We evaluate machine comprehension models' robustness to noise and adversarial attacks by performing novel perturbations at the character, word, and sentence level. We experiment with different amounts of perturbations to examine model…

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

The widespread use of large language models (LLMs) is increasing the demand for methods that detect machine-generated text to prevent misuse. The goal of our study is to stress test the detectors' robustness to malicious attacks under…

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…

Attacks on deep learning models are often difficult to identify and therefore are difficult to protect against. This problem is exacerbated by the use of public datasets that typically are not manually inspected before use. In this paper,…

AI-assisted code review is widely used to detect vulnerabilities before production release. Prior work shows that adversarial prompt manipulation can degrade large language model (LLM) performance in code generation. We test whether similar…

As the AI systems become deeply embedded in social media platforms, we've uncovered a concerning security vulnerability that goes beyond traditional adversarial attacks. It becomes important to assess the risks of LLMs before the general…

Large Language Models have seen rapid progress in capability in recent years; this progress has been accelerating and their capabilities, measured by various benchmarks, are beginning to approach those of humans. There is a strong demand to…

Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learning (ICL). However, the vulnerability of ICL to privacy…

In this paper, we experimentally analyze the robustness of selected Federated Learning (FL) systems in the presence of adversarial clients. We find that temporal attacks significantly affect model performance in the FL models tested,…

We investigate the adversarial robustness of LLMs in transfer learning scenarios. Through comprehensive experiments on multiple datasets (MBIB Hate Speech, MBIB Political Bias, MBIB Gender Bias) and various model architectures (BERT,…

A novel hack involving Large Language Models (LLMs) has emerged, exploiting adversarial suffixes to deceive models into generating perilous responses. Such jailbreaks can trick LLMs into providing intricate instructions to a malicious user…

Large language models (LLMs), known for their capability in understanding and following instructions, are vulnerable to adversarial attacks. Researchers have found that current commercial LLMs either fail to be "harmless" by presenting…