Papers › Shedding More Light on Robust Classifiers under the lens of Energy-based Models

Shedding More Light on Robust Classifiers under the lens of Energy-based Models

8 Jul 2024arXiv:2407.06315archive 2025-07-28

Mujtaba Hussain Mirza, Maria Rosaria Briglia, Senad Beadini, Iacopo Masi

By reinterpreting a robust discriminative classifier as Energy-based Model (EBM), we offer a new take on the dynamics of adversarial training (AT). Our analysis of the energy landscape during AT reveals that untargeted attacks generate adversarial images much more in-distribution (lower energy) than the original data from the point of view of the model. Conversely, we observe the opposite for targeted attacks. On the ground of our thorough analysis, we present new theoretical and practical results that show how interpreting AT energy dynamics unlocks a better understanding: (1) AT dynamic is governed by three phases and robust overfitting occurs in the third phase with a drastic divergence between natural and adversarial energies (2) by rewriting the loss of TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization (TRADES) in terms of energies, we show that TRADES implicitly alleviates overfitting by means of aligning the natural energy with the adversarial one (3) we empirically show that all recent state-of-the-art robust classifiers are smoothing the energy landscape and we reconcile a variety of studies about understanding AT and weighting the loss function under the umbrella of EBMs. Motivated by rigorous evidence, we propose Weighted Energy Adversarial Training (WEAT), a novel sample weighting scheme that yields robust accuracy matching the state-of-the-art on multiple benchmarks such as CIFAR-10 and SVHN and going beyond in CIFAR-100 and Tiny-ImageNet. We further show that robust classifiers vary in the intensity and quality of their generative capabilities, and offer a simple method to push this capability, reaching a remarkable Inception Score (IS) and FID using a robust classifier without training for generative modeling. The code to reproduce our results is available at http://github.com/OmnAI-Lab/Robust-Classifiers-under-the-lens-of-EBM/ .

PaperPDFCodeCode Syntology ranMethod as code

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.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 7 ran (2 with no instrument failure; 5 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

omnai-lab/robust-classifiers-under-the-lens-of-ebm officialmentioned in papermentioned on GitHubpytorchMITSyntology: 10 samples, 7 ran (5 instrument-failed) · 3 unverified report

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.

Code Syntology ran Syntology

10 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · our draft was wrong
2ran
3unverified

Licence: 0 of the 10 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 omnai-lab/robust-classifiers-under-the-lens-of-ebm. “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”. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

omnai-lab/robust-classifiers-under-the-lens-of-ebm official repository 10 samples, 7 ran (5 instrument-failed) · 3 unverified
WEAT_adv Adversarial ML/WEAT_loss.py ran · our draft was wrong MIT (permissive) · fb79541499d1aa7e · report fixture: returned Tensor · level recorded 2026-09-22
call_bn in 5 papers image_generation/norms.py ran MIT (permissive) · 112fb9db5c4e35cc · report fixture: signature bn:callable/0/?, x:Tensor/2/float, update_batch_stats:bool/0/bool · returned Tensor · level recorded 2026-09-24
compute_weights in 10 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 4 of 4, arg 1: rank 2, kind float, dtype float32
Adversarial ML/WEAT_loss.py ran · our draft was wrong fingerprinted MIT (permissive) · f2e90ad69c40bd2a · report fixture: signature energy:Tensor/2/float · returned Tensor · level recorded 2026-09-22
energy_x Adversarial ML/WEAT_loss.py ran · our draft was wrong fingerprinted MIT (permissive) · 3b02bed9d1de1c13 · report fixture: signature logits:Tensor/2/float · returned Tensor · level recorded 2026-09-22
get_norm in 48 papers image_generation/norms.py ran · our draft was wrong MIT (permissive) · 5c287586436a7685 · report fixture: signature n_filters:int/0/int, norm:str/0/str · returned BatchNorm2d · level recorded 2026-09-24
load_tiny_imagenet Robustnes_test/dataset_loader.py ran MIT (permissive) · 68eabfc0ae125aee · report fixture: signature n_examples:int/0/int, data_dir:str/0/str, transforms_test:callable/0/? · returned tuple · level recorded 2026-09-24
ti_ResNet18 Robustnes_test/ti_resnet.py ran · our draft was wrong MIT (permissive) · 33f9787e2217480f · report fixture: signature classes:int/0/int · returned ti_ResNet · level recorded 2026-09-24
load_cifar10 in 20 papers image_generation/utils.py unverified MIT (permissive) · f4b0898be0b428b7 · report
load_cifar100 in 6 papers image_generation/utils.py unverified MIT (permissive) · 681c8eb66d1b4ebc · report
load_svhn Robustnes_test/dataset_loader.py unverified MIT (permissive) · d512774ae8b4915f · report

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. 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Weighted Energy Adversarial Training (WEAT) (graph method: Weighted Energy Adversarial Training (WEAT)). 3 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

  1. WEAT_adv entry · level 1 · ran · our draft was wrong · fb79541499d1aa7e
  2. compute_weights loss · level 1 · ran · our draft was wrong · f2e90ad69c40bd2a
  3. energy_x loss · level 1 · ran · our draft was wrong · 3b02bed9d1de1c13

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="2407.06315") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Adversarial Defense

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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