相关论文: The Devil in the Details: Emergent Misalignment, F…

As large language models (LLMs) continue to advance, ensuring their alignment with human values becomes increasingly critical. Traditional alignment methods heavily rely on human feedback to fine-tune models. With the emergence of…

While large language models are able to retain vast amounts of world knowledge seen during pretraining, such knowledge is prone to going out of date and is nontrivial to update. Furthermore, these models are often used under temporal…

Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings…

With the ever increasing data deluge and the success of deep neural networks, the research of distributed deep learning has become pronounced. Two common approaches to achieve this distributed learning is synchronous and asynchronous weight…

In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set. This phenomenon is called robust overfitting, and it can be observed when…

In this technical report, we evaluate the adversarial robustness of a very recent method called "Geometry-aware Instance-reweighted Adversarial Training"[7]. GAIRAT reports state-of-the-art results on defenses to adversarial attacks on the…

LLMs(Large Language Models) nowadays have widespread adoption as a tool for solving issues across various domain/tasks. These models since are susceptible to produce harmful or toxic results, inference-time adversarial attacks, therefore…

Deep Neural Networks are vulnerable to adversarial attacks even in settings where the attacker has no direct access to the model being attacked. Such attacks usually rely on the principle of transferability, whereby an attack crafted on a…

The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. This becomes particularly evident when LLMs inadvertently generate harmful or toxic content,…

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Large language models (LLMs) have exhibited impressive reasoning abilities on a wide range of complex tasks. However, enhancing these capabilities through post-training remains resource intensive, particularly in terms of data and…

Our goal is to improve reliability of Machine Learning (ML) systems deployed in the wild. ML models perform exceedingly well when test examples are similar to train examples. However, real-world applications are required to perform on any…

Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compromises safety behaviors, including refusal of harmful requests, truthfulness, and…

Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack…

Post-training compression reduces LLM parameter counts but often produces irregular tensor dimensions that degrade GPU performance -- a phenomenon we call \emph{dimensional misalignment}. We present a full-stack analysis tracing root causes…

Recent research shows that fine-tuning on benign instruction-following data can inadvertently undo the safety alignment process and increase a model's propensity to comply with harmful queries. While instruction-following fine-tuning is…

Large Language Models (LLMs) have been applied to Math Word Problems (MWPs) with transformative impacts, revolutionizing how these complex problems are approached and solved in various domains including educational settings. However, the…

This paper presents the system description of our entry for the COLING 2025 FMD challenge, focusing on misinformation detection in financial domains. We experimented with a combination of large language models, including Qwen, Mistral, and…

Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on reducing robust overfitting by using common data augmentation schemes. We…

Existing perceptual similarity metrics assume an image and its reference are well aligned. As a result, these metrics are often sensitive to a small alignment error that is imperceptible to the human eyes. This paper studies the effect of…