14 accepted papers
Reward models (RMs) are fundamental to aligning Large Language Models (LLMs) via human feedback, yet they often suffer from reward hacking. They tend to latch on to superficial or spurious attributes, such as response length or formatting, mistaking these cues learned from correlations in training d…
Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While the large dimensionality of input token space makes it inevita…
Vision-Language Models (VLMs) such as CLIP are trained on large amounts of image-text pairs resulting in remarkable generalization across several data distributions. However in several cases their expensive training and data collection/curation costs do not justify the end application. This motivate…
Large Language Models (LLMs) are typically trained to predict in the forward direction of time. However, recent works have shown that prompting these models to look back and critique their own generations can produce useful feedback. Motivated by this, we explore the question of whether LLMs can be…
Generalization of Neural Networks is crucial for deploying them safely in the real world. Common training strategies to improve generalization involve the use of data augmentations, ensembling and model averaging. In this work, we first establish a surprisingly simple but strong benchmark for genera…
Deep Neural Networks are known to be brittle to even minor distribution shifts compared to the training distribution. While one line of work has demonstrated that \emph{Simplicity Bias} (SB) of DNNs -- bias towards learning only the simplest features -- is a key reason for this brittleness, another…
Visual Question Answering models have been shown to suffer from language biases, where the model learns a correlation between the question and the answer, ignoring the image. While early works attempted to use question-only models or data augmentations to reduce this bias, we propose an adaptive mar…
Adversarial training of Deep Neural Networks is known to be significantly more data-hungry when compared to standard training. Furthermore, complex data augmentations such as AutoAugment, which have led to substantial gains in standard training of image classifiers, have not been successful with Adv…
"The vulnerability of Deep Neural Networks to Adversarial Attacks has fuelled research towards building robust models. While most Adversarial Training algorithms aim at defending attacks constrained within low magnitude Lp norm bounds, real-world adversaries are not limited by such constraints. In t…
Machine learning models deployed as a service (MLaaS) are susceptible to model stealing attacks, where an adversary attempts to steal the model within a restricted access framework. While existing attacks demonstrate near-perfect clone-model performance using softmax predictions of the classificatio…
"Self-supervision has emerged as a propitious method for visual representation learning after the recent paradigm shift from handcrafted pretext tasks to instance-similarity based approaches. Most state-of-the-art methods enforce similarity between various augmentations of a given image, while some…
The vulnerability of Deep Neural Networks to adversarial attacks has spurred immense interest towards improving their robustness. However, present state-of-the-art adversarial defenses involve the use of 10-step adversaries during training, which renders them computationally infeasible for applicati…
Advances in the development of adversarial attacks have been fundamental to the progress of adversarial defense research. Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Adversarial attacks are often generated by maximizing stan…
As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously crafted perturbations that are nearly imperceptible to the hu…