Artificial intelligence systems in critical fields like autonomous driving and medical imaging analysis often continually learn new tasks using a shared stream of input data. For instance, after learning to detect traffic signs, a model may later need to learn to classify traffic lights or different types of vehicles using the same camera feed. This scenario introduces a challenging setting we term Continual Multitask Learning (CMTL), where a model sequentially learns new tasks on an underlying data distribution without forgetting previously learned abilities. Existing continual learning methods often fail in this setting because they learn fragmented, task-specific features that interfere with one another. To address this, we introduce Learning with Preserving (LwP), a novel framework that shifts the focus from preserving task outputs to maintaining the geometric structure of the shared representation space. The core of LwP is a Dynamically Weighted Distance Preservation (DWDP) loss that prevents representation drift by regularizing the pairwise distances between latent data representations. This mechanism of preserving the underlying geometric structure allows the model to retain implicit knowledge and support diverse tasks without requiring a replay buffer, making it suitable for privacy-conscious applications. Extensive evaluations on time-series and image benchmarks show that LwP not only mitigates catastrophic forgetting but also consistently outperforms state-of-the-art baselines in CMTL tasks.

As deep neural networks are deployed in safety-critical domains such as autonomous driving and medical diagnosis, stakeholders need explanations of model behavior that are not only interpretable but also trustworthy with formal guarantees. Existing XAI methods fall short of this requirement: heuristic attribution techniques (e.g., LIME, Integrated Gradients) highlight influential features for individual predictions but offer no mathematical guarantees about decision boundaries, while formal explanation methods verify robustness properties yet remain untargeted, analyzing the nearest boundary regardless of whether it represents a critical risk. In safety-critical systems, however, not all misclassifications carry equal consequences; confusing a “Stop” sign for a “60 kph” sign is far more dangerous than confusing it with a “No Passing” sign. Practitioners therefore lack a principled way to answer a fundamental safety question: how resilient is a model’s classification against a specific, high-risk alternative? We introduce ViTaX (Verified and Targeted Explanations), a formal XAI framework that addresses this gap by generating targeted semifactual explanations with mathematical guarantees. For a given input (class y) and a user-specified critical alternative (class t), ViTaX performs two key steps: (1) it identifies the minimal feature subset most sensitive to the y → t transition using class-specific sensitivity heuristics, and (2) it applies formal reachability analysis to guarantee that perturbing these features by ε is insufficient to flip the classification to t. This guarantee constitutes a verified semifactual: “even if these critical features change by ε classification y persists against t." We formalize this reasoning through Targeted ε-Robustness, a formal property that certifies whether an identified feature subset remains robust under perturbation toward a specific target class. By unifying semifactual explanations, class-specific targeting, and formal verification, ViTaX is the first method to provide formally guaranteed explanations of a model’s resilience against specific, user-identified alternatives. Our evaluations on image classification (MNIST, GTSRB, EMNIST) and regression (TaxiNet) demonstrate that ViTaX achieves significantly higher fidelity (e.g., over 30% improvement) and minimal explanation cardinality compared to existing methods. These results establish ViTaX as a scalable and trustworthy foundation for verifiable, targeted XAI.

Wearable cameras provide an efficient and convenient way to record our lives, supporting real-time documentation and analysis across various domains. Recent research has explored diverse methods for temporal segmentation, which aim to transform unstructured video data into structured events. This transformation facilitates deeper video understanding, optimizes computational resources, and improves the accessibility and interpretability of video content for both machines and humans. However, unlike conventional videos, wearable camera recordings present unique challenges. These include highly unstable camera perspectives, diverse activities across various environments, and flexible duration. As a result, traditional temporal segmentation methods often fail to return effective results. This paper introduces SmartSeg, an unsupervised, non-parametric approach for segmenting wearable camera videos without labeled data. By capturing the fundamental meanings of the video, SmartSeg aggregates the video through the Temporal Self-Similarity Metric encoder and groups sequences of frames into coherent events through clustering techniques. We evaluated SmartSeg on three diverse datasets. We achieved a 50% increase in Mean-over-Frames(MoF) compared to the state-of-the-art on one egocentric dataset. We conducted a real-world case study on nursing simulations, demonstrating SmartSeg’s ability to effectively segment complex, noisy interactions with diverse activity transitions. The results highlight SmartSeg’s robustness in handling long, unstructured, and visually challenging wearable camera videos, establishing it as a promising tool for real-world video temporal segmentation tasks.

Steganography, or hiding messages in plain sight, is a form of information hiding that is most commonly used for covert communication. As modern steganographic mediums include images, text, audio, and video, this communication method is being increasingly used by bad actors to propagate malware, exfiltrate data, and discreetly communicate. Current protection mechanisms rely upon steganalysis, or the detection of steganography, but these approaches are dependent upon prior knowledge, such as steganographic signatures from publicly available tools and statistical knowledge about known hiding methods. These dependencies render steganalysis useless against new or unique hiding methods, which are becoming increasingly common with the application of deep learning models. To mitigate the shortcomings of steganalysis, this work focuses on a deep learning sanitization technique called SUDS that is not reliant upon knowledge of steganographic hiding techniques and is able to sanitize universal and dependent steganography. SUDS is tested using least significant bit method (LSB), dependent deep hiding (DDH), and universal deep hiding (UDH). We demonstrate the capabilities and limitations of SUDS by answering five research questions, including baseline comparisons and an ablation study. Additionally, we apply SUDS to a real-world scenario, where it is able to increase the resistance of a poisoned classifier against attacks by 1375%.