Improving Stability Estimates in Adversarial Explainable AI through Alternate Search Methods

Advances in the effectiveness of machine learning models have come at the cost of enormous complexity resulting in a poor understanding of how they function. Local surrogate methods have been used to approximate the workings of these complex models, but recent work has revealed their vulnerability to adversarial attacks where the explanation produced is appreciably different while the meaning and structure of the complex model's output remains similar. This prior work has focused on the existence of these weaknesses but not on their magnitude. Here we explore using an alternate search method with the goal of finding minimum viable perturbations, the fewest perturbations necessary to achieve a fixed similarity value between the original and altered text's explanation. Intuitively, a method that requires fewer perturbations to expose a given level of instability is inferior to one which requires more. This nuance allows for superior comparisons of the stability of explainability methods.

Towards Robust and Accurate Stability Estimation of Local Surrogate Models in Text-based Explainable AI

Recent work has investigated the concept of adversarial attacks on explainable AI (XAI) in the NLP domain with a focus on examining the vulnerability of local surrogate methods such as Lime to adversarial perturbations or small changes on the input of a machine learning (ML) model. In such attacks, the generated explanation is manipulated while the meaning and structure of the original input remain similar under the ML model. Such attacks are especially alarming when XAI is used as a basis for decision making (e.g., prescribing drugs based on AI medical predictors) or for legal action (e.g., legal dispute involving AI software). Although weaknesses across many XAI methods have been shown to exist, the reasons behind why remain little explored. Central to this XAI manipulation is the similarity measure used to calculate how one explanation differs from another. A poor choice of similarity measure can lead to erroneous conclusions about the stability or adversarial robustness of an XAI method. Therefore, this work investigates a variety of similarity measures designed for text-based ranked lists referenced in related work to determine their comparative suitability for use. We find that many measures are overly sensitive, resulting in erroneous estimates of stability. We then propose a weighting scheme for text-based data that incorporates the synonymity between the features within an explanation, providing more accurate estimates of the actual weakness of XAI methods to adversarial examples.

The Effect of Similarity Measures on Accurate Stability Estimates for Local Surrogate Models in Text-based Explainable AI

Recent work has investigated the vulnerability of local surrogate methods to adversarial perturbations on a machine learning (ML) model's inputs, where the explanation is manipulated while the meaning and structure of the original input remains similar under the complex model. While weaknesses across many methods have been shown to exist, the reasons behind why still remain little explored. Central to the concept of adversarial attacks on explainable AI (XAI) is the similarity measure used to calculate how one explanation differs from another A poor choice of similarity measure can result in erroneous conclusions on the efficacy of an XAI method. Too sensitive a measure results in exaggerated vulnerability, while too coarse understates its weakness. We investigate a variety of similarity measures designed for text-based ranked lists including Kendall's Tau, Spearman's Footrule and Rank-biased Overlap to determine how substantial changes in the type of measure or threshold of success affect the conclusions generated from common adversarial attack processes. Certain measures are found to be overly sensitive, resulting in erroneous estimates of stability.

Privacy Threats in Stable Diffusion Models

This paper introduces a novel approach to membership inference attacks (MIA) targeting stable diffusion computer vision models, specifically focusing on the highly sophisticated Stable Diffusion V2 by StabilityAI. MIAs aim to extract sensitive information about a model's training data, posing significant privacy concerns. Despite its advancements in image synthesis, our research reveals privacy vulnerabilities in the stable diffusion models' outputs. Exploiting this information, we devise a black-box MIA that only needs to query the victim model repeatedly. Our methodology involves observing the output of a stable diffusion model at different generative epochs and training a classification model to distinguish when a series of intermediates originated from a training sample or not. We propose numerous ways to measure the membership features and discuss what works best. The attack's efficacy is assessed using the ROC AUC method, demonstrating a 60\% success rate in inferring membership information. This paper contributes to the growing body of research on privacy and security in machine learning, highlighting the need for robust defenses against MIAs. Our findings prompt a reevaluation of the privacy implications of stable diffusion models, urging practitioners and developers to implement enhanced security measures to safeguard against such attacks.

Focused Adversarial Attacks

Recent advances in machine learning show that neural models are vulnerable to minimally perturbed inputs, or adversarial examples. Adversarial algorithms are optimization problems that minimize the accuracy of ML models by perturbing inputs, often using a model's loss function to craft such perturbations. State-of-the-art object detection models are characterized by very large output manifolds due to the number of possible locations and sizes of objects in an image. This leads to their outputs being sparse and optimization problems that use them incur a lot of unnecessary computation. We propose to use a very limited subset of a model's learned manifold to compute adversarial examples. Our \textit{Focused Adversarial Attacks} (FA) algorithm identifies a small subset of sensitive regions to perform gradient-based adversarial attacks. FA is significantly faster than other gradient-based attacks when a model's manifold is sparsely activated. Also, its perturbations are more efficient than other methods under the same perturbation constraints. We evaluate FA on the COCO 2017 and Pascal VOC 2007 detection datasets.

Preventing Personal Data Theft in Images with Adversarial ML

Facial recognition tools are becoming exceptionally accurate in identifying people from images. However, this comes at the cost of privacy for users of online services with photo management (e.g. social media platforms). Particularly troubling is the ability to leverage unsupervised learning to recognize faces even when the user has not labeled their images. This is made simpler by modern facial recognition tools, such as FaceNet, that use encoders to generate low dimensional embeddings that can be clustered to learn previously unknown faces. In this paper, we propose a strategy to generate non-invasive noise masks to apply to facial images for a newly introduced user, yielding adversarial examples and preventing the formation of identifiable clusters in the embedding space. We demonstrate the effectiveness of our method by showing that various classification and clustering methods cannot reliably cluster the adversarial examples we generate.