Desen Sun

Desen Sun, Shuncheng Jie, Sihang Liu

Diffusion models are a powerful class of generative models that produce images and other content from user prompts, but they are computationally intensive. To mitigate this cost, recent academic and industry work has adopted approximate caching, which reuses intermediate states from similar prompts in a cache. While efficient, this optimization introduces new security risks by breaking isolation among users. This paper provides a comprehensive assessment of the security vulnerabilities introduced by approximate caching. First, we demonstrate a remote covert channel established with the approximate cache, where a sender injects prompts with special keywords into the cache system and a receiver can recover that even after days, to exchange information. Second, we introduce a prompt stealing attack using the approximate cache, where an attacker can recover existing cached prompts from hits. Finally, we introduce a poisoning attack that embeds the attacker's logos into the previously stolen prompt, leading to unexpected logo rendering for the requests that hit the poisoned cache prompts. These attacks are all performed remotely through the serving system, demonstrating severe security vulnerabilities in approximate caching. The code for this work is available.

Chunyang Wang, Desen Sun, Yuebin Bai

Dynamic Graph Neural Networks (DGNNs) have been broadly applied in various real-life applications, such as link prediction and pandemic forecast, to capture both static structural information and temporal characteristics from dynamic graphs. Combining both time-dependent and -independent components, DGNNs manifest substantial parallel computation and data reuse potentials, but suffer from severe memory access inefficiency and data transfer overhead under the canonical one-graph-at-a-time training pattern. To tackle the challenges, we propose PiPAD, a $\underline{\textbf{Pi}}pelined$ and $\underline{\textbf{PA}}rallel$ $\underline{\textbf{D}}GNN$ training framework for the end-to-end performance optimization on GPUs. From both the algorithm and runtime level, PiPAD holistically reconstructs the overall training paradigm from the data organization to computation manner. Capable of processing multiple graph snapshots in parallel, PiPAD eliminates the unnecessary data transmission and alleviates memory access inefficiency to improve the overall performance. Our evaluation across various datasets shows PiPAD achieves $1.22\times$-$9.57\times$ speedup over the state-of-the-art DGNN frameworks on three representative models.

Yuyang Tian, Desen Sun, Yi Ding et al.

As large language models (LLMs) become widely used, their environmental impact, especially carbon emission, has attracted more attention. Prior studies focus on compute-related carbon emissions. In this paper, we find that storage is another key contributor. LLM caching, which saves and reuses KV caches for repeated context, reduces operational carbon by avoiding redundant computation. However, this benefit comes at the cost of embodied carbon from high-capacity, high-speed SSDs. As LLMs scale, the embodied carbon of storage grows significantly. To address this tradeoff, we present GreenCache, a carbon-aware cache management framework that dynamically derives resource allocation plans for LLM serving. GreenCache analyzes the correlation between carbon emission and SLO satisfaction, reconfiguring the resource over time to keep the balance between SLO and carbon emission under dynamic workloads. Evaluations from real traces demonstrate that GreenCache achieves an average carbon reduction of 15.1 % when serving Llama-3 70B in the FR grid, with reductions reaching up to 25.3 %, while staying within latency constraints for > 90 % of requests.

Desen Sun, Jason Hon, Howe Wang et al.

With the rapid advancement of generative AI, users increasingly rely on image-generation models for image design and creation. To achieve faithful outputs, users typically engage in multi-turn interactions during image refinement: a text-to-image generation phase followed by a text-guided image-to-image editing phase. In this paper, we investigate a novel security vulnerability associated with such a workflow. Our key insight is that a nearly invisible hint, like branding information (e.g., a logo), embedded in an input image can be recognized by downstream generative models and subsequently re-rendered onto semantically related objects, even when the user prompt does not explicitly mention it. This form of hidden payload injection makes the attack stealthy. We study two realistic attack scenarios. The first is a phishing-based setting, in which an attacker controls an online image generation service and injects hidden content into generated images before they are returned to users. The second is a poison-based setting, where an attacker distributes a compromised text-to-image diffusion model whose output contains hidden content. We evaluate both attacks using six injected payloads, including well-known logos and customized designs, and demonstrate that the two attacks can achieve success rates of 44.4% and 32.2% on average, respectively, while ensuring the injected logos are visually imperceptible. We also develop a mitigation solution that achieves an average success rate of 87.4% and 92.3% against the phishing-based and poison-based attacks, respectively.

Desen Sun, Henry Tian, Tim Lu et al.

Text-to-Video applications receive increasing attention from the public. Among these, diffusion models have emerged as the most prominent approach, offering impressive quality in visual content generation. However, it still suffers from substantial computational complexity, often requiring several minutes to generate a single video. While prior research has addressed the computational overhead in text-to-image diffusion models, the techniques developed are not directly suitable for video diffusion models due to the significantly larger cache requirements and enhanced computational demands associated with video generation. We present FlexCache, a flexible approximate cache system that addresses the challenges in two main designs. First, we compress the caches before saving them to storage. Our compression strategy can reduce 6.7 times consumption on average. Then we find that the approximate cache system can achieve higher hit rate and computation savings by decoupling the object and background. We further design a tailored cache replacement policy to support the two techniques mentioned above better. Through our evaluation, FlexCache reaches 1.26 times higher throughput and 25% lower cost compared to the state-of-the-art diffusion approximate cache system.

Fanjiang Ye, Zhangke Li, Xinrui Zhong et al.

Diffusion models have emerged as the prevailing approach for text-to-image (T2I) and text-to-video (T2V) generation, yet production platforms must increasingly serve both modalities on shared GPU clusters while meeting stringent latency SLOs. Co-serving such heterogeneous workloads is challenging: T2I and T2V requests exhibit vastly different compute demands, parallelism characteristics, and latency requirements, leading to significant SLO violations in existing serving systems. We present GENSERVE, a co-serving system that leverages the inherent predictability of the diffusion process to optimize serving efficiency. A central insight is that diffusion inference proceeds in discrete, predictable steps and is naturally preemptible at step boundaries, opening a new design space for heterogeneity-aware resource management. GENSERVE introduces step-level resource adaptation through three coordinated mechanisms: intelligent video preemption, elastic sequence parallelism with dynamic batching, and an SLO-aware scheduler that jointly optimizes resource allocation across all concurrent requests. Experimental results show that GENSERVE improves the SLO attainment rate by up to 44% over the strongest baseline across diverse configurations.

Desen Sun, Jason Hon, Jintao Zhang et al.

Diffusion models have demonstrated a remarkable ability in Text-to-Image (T2I) generation applications. Despite the advanced generation output, they suffer from heavy computation overhead, especially for large models that contain tens of billions of parameters. Prior work has illustrated that replacing part of the denoising steps with a smaller model still maintains the generation quality. However, these methods only focus on saving computation for some timesteps, ignoring the difference in compute demand within one timestep. In this work, we propose HybridStitch, a new T2I generation paradigm that treats generation like editing. Specifically, we introduce a hybrid stage that jointly incorporates both the large model and the small model. HybridStitch separates the entire image into two regions: one that is relatively easy to render, enabling an early transition to the smaller model, and another that is more complex and therefore requires refinement by the large model. HybridStitch employs the small model to construct a coarse sketch while exploiting the large model to edit and refine the complex regions. According to our evaluation, HybridStitch achieves 1.83$\times$ speedup on Stable Diffusion 3, which is faster than all existing mixture of model methods.

Fanjiang Ye, Zepeng Zhao, Yi Mu et al.

Diffusion models have recently achieved remarkable success in generative tasks (e.g., image and video generation), and the demand for high-quality content (e.g., 2K/4K videos) is rapidly increasing across various domains. However, generating ultra-high-resolution videos on existing standard-resolution (e.g., 720p) platforms remains challenging due to the excessive re-training requirements and prohibitively high computational and memory costs. To this end, we introduce SuperGen, an efficient tile-based framework for ultra-high-resolution video generation. SuperGen features a novel training-free algorithmic innovation with tiling to successfully support a wide range of resolutions without additional training efforts while significantly reducing both memory footprint and computational complexity. Moreover, SuperGen incorporates a tile-tailored, adaptive, region-aware caching strategy that accelerates video generation by exploiting redundancy across denoising steps and spatial regions. SuperGen also integrates cache-guided, communication-minimized tile parallelism for enhanced throughput and minimized latency. Evaluations demonstrate that SuperGen harvests the maximum performance gains while achieving high output quality across various benchmarks.