Related papers: Stochasticity in Tokenisation Improves Robustness

Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…

To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typically target harmful responses in single-point greedy…

We introduce a scaling law for fine-tuning large language models (LLMs) under fixed compute budgets that explicitly accounts for data composition. Conventional approaches measure training data solely by total tokens, yet the number of…

The work presents an approach for addressing the challenge of robustness in Large Language Models (LLMs) to alterations and potential errors caused by semantically similar but textually different prompts. Recent works have shown that these…

Stochastic embedding transitions introduce a probabilistic mechanism for adjusting token representations dynamically during inference, mitigating the constraints imposed through static or deterministic embeddings. A transition framework was…

Large Language Model (LLM)-generated data is increasingly used in software analytics, but it is unclear how this data compares to human-written data, particularly when models are exposed to adversarial scenarios. Adversarial attacks can…

Large Language Models (LLMs) have showcased remarkable capabilities in following human instructions. However, recent studies have raised concerns about the robustness of LLMs when prompted with instructions combining textual adversarial…

Demonstration-based learning has shown great potential in stimulating pretrained language models' ability under limited data scenario. Simply augmenting the input with some demonstrations can significantly improve performance on few-shot…

This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy. We suggest creating a neighborhood around each training…

Large Language Models (LLMs) have gained widespread adoption across various domains, including chatbots and auto-task completion agents. However, these models are susceptible to safety vulnerabilities such as jailbreaking, prompt injection,…

Most real-world applications that employ deep neural networks (DNNs) quantize them to low precision to reduce the compute needs. We present a method to improve the robustness of quantized DNNs to white-box adversarial attacks. We first…

As Large Language Models make a breakthrough in natural language processing tasks (NLP), multimodal technique becomes extremely popular. However, it has been shown that multimodal NLP are vulnerable to adversarial attacks, where the outputs…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Large Language Models (LLMs) have revolutionized natural language processing, but their robustness against adversarial attacks remains a critical concern. We presents a novel white-box style attack approach that exposes vulnerabilities in…

Large Language Models (LLMs) are widely deployed in real-world applications, yet little is known about their training dynamics at the token level. Evaluation typically relies on aggregated training loss, measured at the batch level, which…

Training large language models (LLMs) from scratch can yield models with unique functionalities and strengths, but it is costly and often leads to redundant capabilities. A more cost-effective alternative is to fuse existing pre-trained…

Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scratch (i.e., with random initializations) using specialized…

Machine learning approaches for speech enhancement are becoming increasingly expressive, enabling ever more powerful modifications of input signals. In this paper, we demonstrate that this expressiveness introduces a vulnerability: advanced…

Deep neural networks for natural language processing are fragile in the face of adversarial examples -- small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction. We…

While transformer-based models achieve strong performance on text classification, we explore whether masking input tokens can further enhance their effectiveness. We propose token masking regularization, a simple yet theoretically motivated…