The use of lightweight drones has surged in recent years across both personal and commercial applications, necessitating the ability to conduct live video analytics on drones with limited computational resources. While edge computing offers a solution to the throughput bottleneck, it also opens the door to potential privacy invasions by exposing sensitive visual data to risks. In this work, we present a lightweight, privacy-preserving framework designed for real-time video analytics. By integrating a novel split-model architecture tailored for distributed deep learning through edge computing, our approach strikes a balance between operational efficiency and privacy. We provide comprehensive evaluations on privacy, object detection, latency, bandwidth usage, and object-tracking performance for our proposed privacy-preserving model.
State-of-the-art generative models exhibit powerful image-generation capabilities, raising ethical and legal challenges for service providers. Consequently, Content Removal Techniques (CRTs) have emerged to control outputs without requiring full retraining. However, the problem of unlearning in Generative Adversarial Networks (GANs) remains largely unexplored. We propose Text-to-Unlearn, a novel framework that selectively unlearns concepts from pre-trained GANs using only text prompts, enabling feature and identity unlearning, as well as fine-grained tasks such as expression and multi-attribute removal in models trained on human faces. Our approach leverages natural language descriptions to guide unlearning without additional datasets or supervised finetuning, offering a scalable solution. To evaluate the effectiveness of our method, we introduce an automated unlearning assessment method using state-of-the-art image–text alignment metrics and propose a new metric: degree of unlearning. Additionally, we assess robustness by introducing adversarial attacks to subvert unlearning. Our results demonstrate that Text-to-Unlearn achieves robust unlearning, resisting adversarial attempts to recover erased concepts while preserving model utility. To our knowledge, this is the first cross-modal unlearning framework for GANs, advancing the management of generative model behavior.
Large language model (LLM) agents are increasingly being employed for offensive cybersecurity tasks such as automated vulnerability discovery, reconnaissance, and penetration testing. This new capability also threatens one of the defender’s most valuable tools: deception. Traditional honeypots rely on realism and obscurity to lure human or script-driven attackers into revealing tactics, techniques, and procedures (TTPs), but LLM-driven attackers can reason about heterogeneous artifacts and use the honeypot suspicion to guide target-selection decisions. We study host-level inference-budget allocation for LLM penetration-testing agents facing honeypot uncertainty, using a heuristic policy that couples detector evidence, vulnerability severity, realized host-specific cost, and post-connect verification. We formalize the attacker’s problem as a budgeted decision process: an agent interacts with potential targets, consuming LLM execution budget during reconnaissance and exploitation, and must decide whether to engage (continue exploitation) or disengage (skip) when honeypot suspicion arises. In a controlled mixed-host testbed, we examine detector behavior, target ranking, post-entry expenditure, and genuine-host confirmations. In the evaluated testbed, the proposed policy achieves higher mean genuine-host confirmation counts than the baselines, with the LLM attacker configuration held constant across policies. While defenses are beyond our present scope, we discuss implications for future adversarially resilient and adaptive honeypot design.