{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sponge-examples-energy-latency-attacks-on","title":"Sponge Examples: Energy-Latency Attacks on Neural Networks","arxiv_id":"2006.03463","date":"2020-06-05","proceeding":null,"authors":["Ilia Shumailov","Yiren Zhao","Daniel Bates","Nicolas Papernot","Robert Mullins","Ross Anderson"],"abstract":"The high energy costs of neural network training and inference led to the use of acceleration hardware such as GPUs and TPUs. While this enabled us to train large-scale neural networks in datacenters and deploy them on edge devices, the focus so far is on average-case performance. In this work, we introduce a novel threat vector against neural networks whose energy consumption or decision latency are critical. We show how adversaries can exploit carefully crafted $\\boldsymbol{sponge}~\\boldsymbol{examples}$, which are inputs designed to maximise energy consumption and latency. We mount two variants of this attack on established vision and language models, increasing energy consumption by a factor of 10 to 200. Our attacks can also be used to delay decisions where a network has critical real-time performance, such as in perception for autonomous vehicles. We demonstrate the portability of our malicious inputs across CPUs and a variety of hardware accelerator chips including GPUs, and an ASIC simulator. We conclude by proposing a defense strategy which mitigates our attack by shifting the analysis of energy consumption in hardware from an average-case to a worst-case perspective.","url_abs":"https://arxiv.org/abs/2006.03463v2","url_pdf":"https://arxiv.org/pdf/2006.03463v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sponge-examples-energy-latency-attacks-on","repo_url":"https://github.com/iliaishacked/sponge_examples","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sponge-examples-energy-latency-attacks-on","repo_url":"https://github.com/and-mill/2024-sponge-example-analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.03463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03463"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/and-mill/2024-sponge-example-analysis","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iliaishacked/sponge_examples","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"4f3d097886486499","entry":"get_energy_estimate","repo":"iliaishacked/sponge_examples","repo_kind":"official","path":"energy_estimator/analyse.py","file_url":"https://github.com/iliaishacked/sponge_examples/blob/HEAD/energy_estimator/analyse.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f3d097886486499"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}