The massive deployment of Machine Learning (ML) models has been accompanied by the emergence of several attacks that threaten their trustworthiness and raise ethical and societal concerns such as invasion of privacy, discrimination risks, and lack of accountability. Model hijacking is one of these attacks, where the adversary aims to hijack a victim model to execute a different task than its original one. Model hijacking can cause accountability and security risks since a hijacked model owner can be framed for having their model offering illegal or unethical services. Prior state-of-the-art works consider model hijacking as a training time attack, whereby an adversary requires access to the ML model training to execute their attack. In this paper, we consider a stronger threat model where the attacker has no access to the training phase of the victim model. Our intuition is that ML models, typically over-parameterized, might (unintentionally) learn more than the intended task for they are trained. We propose a simple approach for model hijacking at inference time named SnatchML to classify unknown input samples using distance measures in the latent space of the victim model to previously known samples associated with the hijacking task classes. SnatchML empirically shows that benign pre-trained models can execute tasks that are semantically related to the initial task. Surprisingly, this can be true even for hijacking tasks unrelated to the original task. We also explore different methods to mitigate this risk. We first propose a novel approach we call meta-unlearning, designed to help the model unlearn a potentially malicious task while training on the original task dataset. We also provide insights on over-parameterization as one possible inherent factor that makes model hijacking easier, and we accordingly propose a compression-based countermeasure against this attack.

This study thoroughly investigates how well deep learning models can recognize Arabic handwritten text for person biometric identification. It compares three advanced architectures -- ResNet50, MobileNetV2, and EfficientNetB7 -- using three widely recognized datasets: AHAWP, Khatt, and LAMIS-MSHD. Results show that EfficientNetB7 outperforms the others, achieving test accuracies of 98.57\%, 99.15\%, and 99.79\% on AHAWP, Khatt, and LAMIS-MSHD datasets, respectively. EfficientNetB7's exceptional performance is credited to its innovative techniques, including compound scaling, depth-wise separable convolutions, and squeeze-and-excitation blocks. These features allow the model to extract more abstract and distinctive features from handwritten text images. The study's findings hold significant implications for enhancing identity verification and authentication systems, highlighting the potential of deep learning in Arabic handwritten text recognition for person biometric identification.

Photoplethysmography (PPG) signals, typically acquired from wearable devices, hold significant potential for continuous fitness-health monitoring. In particular, heart conditions that manifest in rare and subtle deviating heart patterns may be interesting. However, robust and reliable anomaly detection within these data remains a challenge due to the scarcity of labeled data and high inter-subject variability. This paper introduces a two-stage framework leveraging representation learning and personalization to improve anomaly detection performance in PPG data. The proposed framework first employs representation learning to transform the original PPG signals into a more discriminative and compact representation. We then apply three different unsupervised anomaly detection methods for movement detection and biometric identification. We validate our approach using two different datasets in both generalized and personalized scenarios. The results show that representation learning significantly improves anomaly detection performance while reducing the high inter-subject variability. Personalized models further enhance anomaly detection performance, underscoring the role of personalization in PPG-based fitness-health monitoring systems. The results from biometric identification show that it's easier to distinguish a new user from one intended authorized user than from a group of users. Overall, this study provides evidence of the effectiveness of representation learning and personalization for anomaly detection in PPG data.

Iris-based identification systems are among the most popular approaches for person identification. Such systems require good-quality segmentation modules that ideally identify the regions for different eye components. This paper introduces the new two-headed architecture, where the eye components and eyelashes are segmented using two separate decoding modules. Moreover, we investigate various training scenarios by adopting different training losses. Thanks to the two-headed approach, we were also able to examine the quality of the model with the convex prior, which enforces the convexity of the segmented shapes. We conducted an extensive evaluation of various learning scenarios on real-life conditions high-resolution near-infrared iris images.

It's been almost one year since the European Commission unveiled the draft for what may well be one of the most influential legal frameworks in the world: the EU AI Act. According to the Mozilla Foundation, the framework is still work in progress, and now is the time to actively engage in the effort to shape its direction. Mozilla Foundation's stated mission is to work to ensure the internet remains a public resource that is open and accessible to everyone. Since 2019, Mozilla Foundation has focused a significant portion of its internet health movement-building programs on AI. We met with Mozilla Foundation's Executive Director Mark Surman and Senior Policy Researcher Maximilian Gahntz to discuss Mozilla's focus and stance on AI, key facts about the EU AI Act and how it will work in practice, as well as Mozilla's recommendations for improving it, and ways for everyone be involved in the process.

"A model is as good as the underlying data," said Jayachandran Ramachandran, SVP of Artificial Intelligence Labs at Course5 Intelligence during his MLDS talk "Will evolving regulations stymie AI innovations? He discussed how industries and governments recognise this problem and develop regulations and recommendations. He also touched on the recommendations and implications crelated to European Union's AI regulations draft. Today, most countries have an AI policy and strategies in place. The EU is at the forefront of AI regulations and drafts. "The EU draft in 2021 is acting as a benchmark for other countries," Ramachandran noted. The draft seeks to ensure the AI policy is human-centric, sustainable, secure, inclusive and trustworthy. Additionally, the draft focuses on a seamless transition of AI from the lab to the market. Any system deployed for the users based in the EU will be under the scope of this AI regulation. If the consumers are based outside the EU, they will not be held ...

When it comes to identification, I think there's been a lot of gains in terms of testing the accuracy of different kinds of software, right. AI software that does facial recognition, or other kinds of biometric identification. NIST, the Department of Commerce, for example, has tests that they actually publish the results of different kinds of software. And the sort of background concern there is accuracy, obviously, but also bias, particularly if some of the algorithms are not as good or as accurate when it comes to, for example, certain racial groups. And that's also the kind of information that this puts out.

Although it claims to protect our liberties, the EU's draft text on artificial intelligence (AI), presented by Margrethe Vestager, actually promotes the accelerated development of all aspects of AI, in particular for security purposes. Loaded with exceptions, resting on a stale risk-based approach, and picking up the French government's rhetoric on the need for more experimentation, this text should be modified down to its foundation. In its current state it risks endangering the slim legal protections that European law holds out in face of the massive deployment of surveillance techniques in public space. On April 21, 2021 the European Commission (EC) published a regulation proposal for a "European approach" to AI, accompanied by a coordinating plan to guide member states' action for the years to come. Beyond the rethoric of the European Commission, the draft regulation is deeply insufficient in how it treats the danger that AI systems represent for fundamental freedoms.

The Transform Technology Summits start October 13th with Low-Code/No Code: Enabling Enterprise Agility. This week, The European Parliament, the body responsible for adopting European Union (EU) legislation, passed a non-binding resolution calling for a ban on law enforcement use of facial recognition technology in public places. The resolution, which also proposes a moratorium on the deployment of predictive policing software, would restrict the use of remote biometric identification unless it's to fight "serious" crime, such as kidnapping and terrorism. The approach stands in contrast to that of U.S. agencies, which continue to embrace facial recognition even in light of studies showing the potential for ethnic, racial, and gender bias. A recent report from the U.S. Government Accountability Office found that 10 branches including the Departments of Agriculture, Commerce, Defense, and Homeland Security plan to expand their use of facial recognition between 2020 and 2023 as they implement as many as 17 different facial recognition systems.

Some of the most powerful investors in Silicon Valley want to scan your eyeball. You almost certainly shouldn't let them. OpenAI CEO Sam Altman, LinkedIn co-founder Reid Hoffmann, and major venture capital firm Andreesen Horowitz are all backing a recently revealed plan by a company called Worldcoin, which mashes up three big ideas: It's a cryptocurrency company, and it's a Universal Basic Income project, and also it's a biometric-scanning company. If, first, the world will share its irises. According to a recent report by Bloomberg, Worldcoin's goal is to use cryptocurrency as way to spread money more equitably around the world in a setup similar to a universal basic income.