Traditional maximally permissive deadlock prevention control for flexible manufacturing systems requires costly reachability analysis. It has been a hot race to synthesise optimal controllers to be maximally permissive with fewest monitors. Previous work shows that among all n ‐dependent siphons, only one siphon (whose unmarked state follows some token distribution) needs to be controlled. This greatly simplifies the supervisor synthesis as well as minimises the number of monitors required while making the controlled net maximally permissive (i.e. all live states can be reached.). This study further proposes a maximally permissive control policy for a subclass of systems of simple sequential processes with resources (S 3 PR) based on the above theory of token distribution pattern of unmarked siphons.
The deployment of deepfake face-swapping technology has matured, becoming widespread on the Internet. The misuse of this technology raises significant concerns for application security and privacy. To counter deepfake threats, we propose a sugar-coated poison defense targeting the latent vectors of generative models. This strategy aims to impact visual effects without substantially increasing reconstruction loss. We establish metrics for visual effects and reconstruction loss to assess perturbation effects on latent vectors, emphasizing those with the most significant impact on visual effects while minimizing reconstruction loss. Our approach begins by utilizing a facial feature extraction model to convert faces into latent representations. We then introduce two latent selection methods: 1) shap-based latent selection using a linear regression model for approximation, and 2) grid search latent selection employing heuristics of adversarial attacks. These methods pinpoint vectors that, when perturbed, can increase face landmark distances while maintaining low mean square errors, commonly used as the optimization metric in deepfake reconstruction models. We apply inconsistent perturbations to selected latent vectors in video frames, acting as sugar-coated poison for deepfake face-swapping applications. Preliminary results demonstrate that these perturbations can be applied to individual videos, resulting in low reconstruction loss. Importantly, they induce measurable consistency reduction in deepfake videos, making them more discernible and accessible to identify.
The predictive capabilities of machine learning models have improved significantly in recent years, leading to their widespread use in various fields. However, these models remain vulnerable to adversarial attacks, where carefully crafted inputs can mislead predictions and compromise the security of critical systems. Therefore, it is crucial to develop effective methods for detecting and preventing such attacks. Given that many neural network models are implemented using Python, this study addresses the issue of detecting adversarial examples from a new perspective by investigating information leakage in their Python model executions. To realize this objective, we propose a novel Python interpreter that utilizes Python bytecode instrumentation to profile layer-wise instruction-level program executions. We then search for information leakage on both legal and adversarial inputs, identifying their side-channel differences in call executions (i.e., call count, return values, and execution time) and synthesize the detection rule accordingly. Our approach is evaluated against TorchAttacks, AdvDoor, and RNN-Test attacks, targeting various models and applications. Our findings indicate that while there is call-return-value leakage on TorchAttacks images, there is no leakage to detect AdvDoor and RNN-Test attacks based on execution time or return values of string, integer, float, and Boolean type functions.