Papers › HYDRA: Pruning Adversarially Robust Neural Networks
HYDRA: Pruning Adversarially Robust Neural Networks
Vikash Sehwag, Shiqi Wang, Prateek Mittal, Suman Jana
In safety-critical but computationally resource-constrained applications, deep learning faces two key challenges: lack of robustness against adversarial attacks and large neural network size (often millions of parameters). While the research community has extensively explored the use of robust training and network pruning independently to address one of these challenges, only a few recent works have studied them jointly. However, these works inherit a heuristic pruning strategy that was developed for benign training, which performs poorly when integrated with robust training techniques, including adversarial training and verifiable robust training. To overcome this challenge, we propose to make pruning techniques aware of the robust training objective and let the training objective guide the search for which connections to prune. We realize this insight by formulating the pruning objective as an empirical risk minimization problem which is solved efficiently using SGD. We demonstrate that our approach, titled HYDRA, achieves compressed networks with state-of-the-art benign and robust accuracy, simultaneously. We demonstrate the success of our approach across CIFAR-10, SVHN, and ImageNet dataset with four robust training techniques: iterative adversarial training, randomized smoothing, MixTrain, and CROWN-IBP. We also demonstrate the existence of highly robust sub-networks within non-robust networks. Our code and compressed networks are publicly available at https://github.com/inspire-group/compactness-robustness.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Syntology holds a reference implementation of HYDRA, generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='HYDRA') (how to connect); the free check have('2002.10509') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2002.10509")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2002.10509", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2002.10509")
Code
The archive's official repository (inspire-group/compactness-robustness) was not harvested; the 19 samples below come from 2 community repositories.
Syntology 19 code samples harvested from 2 repositories linked to this paper: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 15 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.
By repository: community (archive-listed): 19 samples from 2 repositories, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:
- optml-group/bip, community (archive-listed): harvested for another paper, listed under the repository
Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
19 samples harvested: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 15 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 17 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
9c06e50d9e8c334e · report
fixture: returned GetSubnet · level recorded 2026-09-22 7440b4e5bc3f91bc · report
fixture: returned Interval_BN · level recorded 2026-09-22 95be6efd42f19c4d · report
727eb7c9df20157d · report
c24d64ff812f33fb · report
e3fcced1e96eb0f2 · report
001e355f33be54d7 · report
f6c5efd14db6201c · report
7b61dbf5d4a8dbd0 · report
a65a8d15783b7474 · report
f108d8edefeb2b08 · report
f62e45a681df257c · report
0ba759110f8efeb7 · report
01f2161a52449ec4 · report
cfe05853a4302ca5 · report
c2a80e1b6f39c437 · report
9e06a651cf81f00f · report
3c96583f581f4d37 · report
fixture: returned GetSubnet · level recorded 2026-09-22 9fa88431a218cf84 · report
fixture: returned SubnetConv · level recorded 2026-09-22 Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.
3 assemblies on this paper: 2 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).
generated Assembly for HYDRA (graph method: HYDRA), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).
label matches by construction: the code was generated for this method (not judged by a model)
- hydra_score_initialization entry · level 2 · ran ·
c7f3a776cc4f65f584211c53dd4e5925a11f57275cd5a28701763982c28cf799
2 sibling assemblies for HYDRA (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for HYDRA (graph method: HYDRA). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 2 siblings
- SubnetConv entry · level 1 · ran ·
9fa88431a218cf84 - GetSubnet helper · level 1 · ran ·
3c96583f581f4d37
harvested Assembly for HYDRA (graph method: HYDRA). 17 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 15 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
one of 2 siblings
- Interval_Bound entry · level 0 · unverified ·
727eb7c9df20157d - Center_symbolic_interval helper · level 0 · unverified ·
95be6efd42f19c4d - Interval_network helper · level 0 · unverified ·
f108d8edefeb2b08 - Inverse_interval helper · level 0 · unverified ·
f62e45a681df257c - Symbolic_interval helper · level 0 · unverified ·
0ba759110f8efeb7 - Symbolic_interval_proj1 helper · level 0 · unverified ·
01f2161a52449ec4 - Symbolic_interval_proj2 helper · level 0 · unverified ·
cfe05853a4302ca5 - gen_sym helper · level 0 · unverified ·
c2a80e1b6f39c437 - mix_interval helper · level 0 · unverified ·
9e06a651cf81f00f - Interval_BN model · level 1 · ran ·
7440b4e5bc3f91bc - Interval_Conv2d model · level 0 · unverified ·
c24d64ff812f33fb - Interval_Dense model · level 0 · unverified ·
e3fcced1e96eb0f2 - Interval_Flatten model · level 0 · unverified ·
001e355f33be54d7 - Interval_ReLU model · level 0 · unverified ·
f6c5efd14db6201c - Interval_SubConv helper · level 0 · unverified ·
7b61dbf5d4a8dbd0 - Interval_SubLinear helper · level 0 · unverified ·
a65a8d15783b7474 - GetSubnet helper · level 1 · ran ·
9c06e50d9e8c334e
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2002.10509") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections