CoSimRec: Measuring Coordinated-Content Penetration in Recommender Feedback Loops

Recommender systems increasingly shape which content reaches users, making it important to understand whether coordinated activity is amplified beyond the accounts that initiate it. Existing robustness evaluations largely focus on static target-rank changes and do not capture how coordinated interactions, recommendation, and user response evolve within a feedback loop. To address this gap, we propose CoSimRec, an offline agent-based evaluation framework that models coordinated accounts, dynamic ranking, non-bot responses, and ranking interventions in a shared closed-loop process. CoSimRec introduces the Algorithmic Penetration Rate (APR) metric family to measure target content's share of non-bot exposure and engagement, lift against matched no-attack baselines, and exposure gained per coordinated interaction. We evaluate CoSimRec on MIND, MovieLens, and LastFM using random, popularity-based, feedback-sensitive, MF, and BPR-MF recommenders, with ten-seed inference for the primary APR analysis and population-scale experiments of up to 1000 users. Random controls show no statistically supported positive penetration, whereas popularity-based and feedback-sensitive ranking produce significant positive APR-Lift in all six master-worker dataset--recommender settings, reaching 0.4505 on LastFM; synchronization-aware ranking reduces APR in every corresponding defense setting.

Embedded Arena: Iterative Optimization via Hardware Feedback

Embedded devices from wildlife monitoring stations to clinical wearables require local AI inference due to latency, communication, or privacy constraints. Optimizing models for heterogeneous microcontrollers (MCUs) requires simultaneously satisfying hard physical constraints on memory, power, and temperature while preserving accuracy, a multidimensional optimization that is today performed manually by experts. We ask whether an LLM agent can autonomously navigate this complex, multi-turn pipeline guided by real hardware feedback, and introduce a hardware-in-the-loop agent arena in which the agent iteratively refines both model and firmware -- compiling, flashing, and measuring on real hardware -- to enable closed-loop optimization. Frontier models, including Claude Opus 4.7 and Gemini 3.1 Pro, fail entirely without hardware feedback (0% deployment success), whereas our hardware-in-the-loop formulation achieves the first successful deployment within three iterations and can surpass human expert results within seven. This agentic co-optimization achieves 250x compression for vision models with <3.3% accuracy loss and 400x for audio with <6% Feature Error Rate loss, enabling battery-free operation on a commercial MCU via solar harvesting. We demonstrate practical impact in two real-world systems: an elk-detection camera trap (96.7% accuracy) and a phonetic-transcription wearable (8.44% FER) for child development research.

MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs

Multimodal Large Language Models (MLLMs) have achieved remarkable performance but remain vulnerable to jailbreak attacks that can induce harmful content and undermine their secure deployment. Previous studies have shown that introducing additional inference steps, which disrupt security attention, can make MLLMs more susceptible to being misled into generating malicious content. However, these methods rely on single-image masking or isolated visual cues, which only modestly extend reasoning paths and thus achieve limited effectiveness, particularly against strongly aligned commercial closed-source models. To address this problem, in this paper, we propose Multi-Image Dispersion and Semantic Reconstruction (MIDAS), a multimodal jailbreak framework that decomposes harmful semantics into risk-bearing subunits, disperses them across multiple visual clues, and leverages cross-image reasoning to gradually reconstruct the malicious intent, thereby bypassing existing safety mechanisms. The proposed MIDAS enforces longer and more structured multi-image chained reasoning, substantially increases the model's reliance on visual cues while delaying the exposure of malicious semantics and significantly reducing the model's security attention, thereby improving the performance of jailbreak against advanced MLLMs. Extensive experiments across different datasets and MLLMs demonstrate that the proposed MIDAS outperforms state-of-the-art jailbreak attacks for MLLMs and achieves an average attack success rate of 81.46% across 4 closed-source MLLMs. Our code is available at this [link](https://github.com/Winnie-Lian/MIDAS).