Haniyeh Ehsani Oskouie

Haniyeh Ehsani Oskouie, Sajjad Ghiasvand, Lionel Levine et al.

As Artificial Intelligence (AI) models are increasingly integrated into critical systems, the need for a robust framework to establish the trustworthiness of AI is increasingly paramount. While collaborative efforts have established conceptual foundations for such a framework, there remains a significant gap in developing concrete, technically robust methods for assessing AI model quality and performance. This paper introduces a novel approach for assessing a newly trained model's performance based on another known model by calculating correlation between neural networks. The proposed method evaluates correlations by determining if, for each neuron in one network, there exists a neuron in the other network that produces similar output. This approach has implications for memory efficiency, allowing for the use of smaller networks when high correlation exists between networks of different sizes. Experiments on five fully connected networks and a two layer CNN trained on MNIST family datasets show that higher alignment with the CNN tracks stronger performance and smaller degradation under black box transfer based attacks. On ImageNet pretrained ResNets and DenseNets, partial layer comparisons recover intuitive architectural affinities, indicating that the procedure scales with reasonable approximations. These results support representational alignment as a lightweight compatibility check that complements standard accuracy, calibration, and robustness evaluations and enables early external validation of new models. Code is available at https://github.com/aheldis/Cross-model-Correlation.git.

Haniyeh Ehsani Oskouie, Christina Chance, Claire Huang et al.

Content moderation and toxicity classification represent critical tasks with significant social implications. However, studies have shown that major classification models exhibit tendencies to magnify or reduce biases and potentially overlook or disadvantage certain marginalized groups within their classification processes. Researchers suggest that the positionality of annotators influences the gold standard labels in which the models learned from propagate annotators' bias. To further investigate the impact of annotator positionality, we delve into fine-tuning BERTweet and HateBERT on the dataset while using topic-modeling strategies for content moderation. The results indicate that fine-tuning the models on specific topics results in a notable improvement in the F1 score of the models when compared to the predictions generated by other prominent classification models such as GPT-4, PerspectiveAPI, and RewireAPI. These findings further reveal that the state-of-the-art large language models exhibit significant limitations in accurately detecting and interpreting text toxicity contrasted with earlier methodologies. Code is available at https://github.com/aheldis/Toxicity-Classification.git.

Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Mahnoosh Alizadeh et al.

Vision-Language Models (VLMs) such as CLIP have shown remarkable performance in cross-modal tasks through large-scale contrastive pre-training. To adapt these large transformer-based models efficiently for downstream tasks, Parameter-Efficient Fine-Tuning (PEFT) techniques like (Low-Rank Adaptation) LoRA have emerged as scalable alternatives to full fine-tuning, especially in few-shot scenarios. However, like traditional deep neural networks, VLMs are highly vulnerable to adversarial attacks, where imperceptible perturbations can significantly degrade model performance. Adversarial training remains the most effective strategy for improving model robustness in PEFT. In this work, we propose AdvCLIP-LoRA, to our knowledge the first method designed to enhance the adversarial robustness of CLIP models fine-tuned with LoRA in few-shot settings. Our method formulates training as a minimax optimization over low-rank adapters and adversarial perturbations, enabling robust adaptation with a small trainable footprint. Across eight datasets and two backbones (ViT-B/16 and ViT-B/32), AdvCLIP-LoRA achieves state-of-the-art performance in few-shot classification, adversarial base-to-new generalization, and cross-dataset transfer, delivering higher adversarial robustness than prompt tuning baselines without sacrificing much clean accuracy. These findings highlight AdvCLIP-LoRA as a practical approach for robust adaptation of VLMs in resource-constrained settings.

Dong Lao, Yuxiang Zhang, Haniyeh Ehsani Oskouie et al.

We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead to information loss, we propose to "combat noise with noise" by leveraging stochastic resonance to enhance robustness while minimizing information loss. Our approach introduces small translational perturbations to the input image, aligns the transformed feature embeddings, and aggregates them before mapping back to the original reference image. This can be expressed in a closed-form formula, which can be deployed on diverse existing network architectures without introducing additional network modules or fine-tuning for specific attack types. The resulting method is entirely training-free, architecture-agnostic, and attack-agnostic. Empirical results show state-of-the-art robustness on image classification and, for the first time, establish a generic test-time defense for dense prediction tasks, including stereo matching and optical flow, highlighting the method's versatility and practicality. Specifically, relative to clean (unperturbed) performance, our method recovers up to 68.1% of the accuracy loss on image classification, 71.9% on stereo matching, and 29.2% on optical flow under various types of adversarial attacks.

Arya Hatamian, Lionel Levine, Haniyeh Ehsani Oskouie et al.

Having a sufficient quantity of quality data is a critical enabler of training effective machine learning models. Being able to effectively determine the adequacy of a dataset prior to training and evaluating a model's performance would be an essential tool for anyone engaged in experimental design or data collection. However, despite the need for it, the ability to prospectively assess data sufficiency remains an elusive capability. We report here on two experiments undertaken in an attempt to better ascertain whether or not basic descriptive statistical measures can be indicative of how effective a dataset will be at training a resulting model. Leveraging the effect size of our features, this work first explores whether or not a correlation exists between effect size, and resulting model performance (theorizing that the magnitude of the distinction between classes could correlate to a classifier's resulting success). We then explore whether or not the magnitude of the effect size will impact the rate of convergence of our learning rate, (theorizing again that a greater effect size may indicate that the model will converge more rapidly, and with a smaller sample size needed). Our results appear to indicate that this is not an effective heuristic for determining adequate sample size or projecting model performance, and therefore that additional work is still needed to better prospectively assess adequacy of data.