Related papers: Smoothed Embeddings for Robust Language Models
Large Language Models (LLMs) are increasingly being integrated into services such as ChatGPT to provide responses to user queries. To mitigate potential harm and prevent misuse, there have been concerted efforts to align the LLMs with human…
Guard models are a critical component of LLM safety, but their sensitivity to superficial linguistic variations remains a key vulnerability. We show that even meaning-preserving paraphrases can cause large fluctuations in safety scores,…
The organization of latent token representations plays a crucial role in determining the stability, generalization, and contextual consistency of language models, yet conventional approaches to embedding refinement often rely on parameter…
Recent provably secure linguistic steganography (PSLS) methods rely on mainstream autoregressive language models (ARMs) to address historically challenging tasks, that is, to disguise covert communication as ``innocuous'' natural language…
As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…
The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to data cleaning and curation, well-constructed LLMs have been…
We propose a novel approach for training large language models (LLMs) to adhere to objectives defined within a latent embedding space. Our method leverages reinforcement learning (RL), treating a pre-trained LLM as an environment. Our…
Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…
Deep learning-based malware detection systems are vulnerable to adversarial EXEmples - carefully-crafted malicious programs that evade detection with minimal perturbation. As such, the community is dedicating effort to develop mechanisms to…
Ensembling Large Language Models (LLMs) has gained attention as a promising approach to surpass the performance of individual models by leveraging their complementary strengths. In particular, aggregating models' next-token probability…
Randomized smoothing (RS) has been shown to be a fast, scalable technique for certifying the robustness of deep neural network classifiers. However, methods based on RS require augmenting data with large amounts of noise, which leads to…
Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To address this vulnerability, we propose MirrorCheck, a…
Large language models (LLMs) have exhibited outstanding performance in natural language processing tasks. However, these models remain susceptible to adversarial attacks in which slight input perturbations can lead to harmful or misleading…
Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…
Randomized smoothing is a popular certified defense against adversarial attacks. In its essence, we need to solve a problem of statistical estimation which is usually very time-consuming since we need to perform numerous (usually $10^5$)…
Masked Language Models (MLM) are self-supervised neural networks trained to fill in the blanks in a given sentence with masked tokens. Despite the tremendous success of MLMs for various text based tasks, they are not robust for spoken…
Converting different modalities into general text, serving as input prompts for large language models (LLMs), is a common method to align multimodal models when there is limited pairwise data. This text-centric approach leverages the unique…
Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for defending against jailbreak attacks are primarily based on auxiliary models. These strategies, however, often require extensive data collection or…
The increasing deployment of Large Language Models (LLMs) across enterprise and mission-critical domains has underscored the urgent need for robust guardrailing systems that ensure safety, reliability, and compliance. Existing solutions…
Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…