Papers › AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning

AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning

8 Nov 2018arXiv:1811.03194archive 2025-07-28

Florian Tramèr, Pascal Dupré, Gili Rusak, Giancarlo Pellegrino, Dan Boneh

Perceptual ad-blocking is a novel approach that detects online advertisements based on their visual content. Compared to traditional filter lists, the use of perceptual signals is believed to be less prone to an arms race with web publishers and ad networks. We demonstrate that this may not be the case. We describe attacks on multiple perceptual ad-blocking techniques, and unveil a new arms race that likely disfavors ad-blockers. Unexpectedly, perceptual ad-blocking can also introduce new vulnerabilities that let an attacker bypass web security boundaries and mount DDoS attacks. We first analyze the design space of perceptual ad-blockers and present a unified architecture that incorporates prior academic and commercial work. We then explore a variety of attacks on the ad-blocker's detection pipeline, that enable publishers or ad networks to evade or detect ad-blocking, and at times even abuse its high privilege level to bypass web security boundaries. On one hand, we show that perceptual ad-blocking must visually classify rendered web content to escape an arms race centered on obfuscation of page markup. On the other, we present a concrete set of attacks on visual ad-blockers by constructing adversarial examples in a real web page context. For seven ad-detectors, we create perturbed ads, ad-disclosure logos, and native web content that misleads perceptual ad-blocking with 100% success rates. In one of our attacks, we demonstrate how a malicious user can upload adversarial content, such as a perturbed image in a Facebook post, that fools the ad-blocker into removing another users' non-ad content. Moving beyond the Web and visual domain, we also build adversarial examples for AdblockRadio, an open source radio client that uses machine learning to detects ads in raw audio streams.

PaperPDFCodeCode Syntology ran

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 15 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 15 samples from 1 repository, 11 ran (11 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.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ftramer/ad-versarial officialmentioned in papermentioned on GitHubtfMITSyntology: 15 samples, 11 ran (0 instrument-failed) · 4 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

15 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “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.

11ran
4unverified

Licence: 0 of the 15 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 ftramer/ad-versarial. “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.

ftramer/ad-versarial official repository 15 samples, 11 ran (0 instrument-failed) · 4 unverified
batch_eval page-based/utils.py ran MIT (permissive) · 7471ef5863e35839 · report fixture: signature sess:Session/0/?, tf_outputs:list/1/SymbolicTensor, feed_dict:dict/0/?, batch_size:int/0/int, extra_feed:NoneType/0/? · returned list · level recorded 2026-09-25
batch_eval_ch page-based/utils.py ran MIT (permissive) · 1f1b48c13ddfd7f1 · report fixture: signature sess:Session/0/?, tf_inputs:list/1/SymbolicTensor, tf_outputs:list/1/SymbolicTensor, numpy_inputs:list/1/ndarray, batch_size:int/0/int, feed:NoneType/0/? · returned list · level recorded 2026-09-25
blend_white element-frame-based/utils.py ran MIT (permissive) · 6f84e0253750d23a · report fixture: signature img:ndarray/3/int · returned ndarray · level recorded 2026-09-25
compare_hash in 6 papers element-frame-based/phash/model.py ran fingerprinted MIT (permissive) · 35ac26a4707546ca · report fixture: signature h1:ndarray/2/int, h2:ndarray/2/int · returned float64 · level recorded 2026-09-25
is_equal in 8 papers element-frame-based/exact_match.py ran MIT (permissive) · f7a281adc4fb2f95 · report fixture: signature img1:ndarray/3/float, img2:ndarray/3/float · returned bool · level recorded 2026-09-25
load_image in 273 papers page-based/utils.py ran MIT (permissive) · b7e77d2bb35e1278 · report fixture: signature image_file:str/0/str · returned ndarray · level recorded 2026-09-25
remove_alpha element-frame-based/phash/model.py ran fingerprinted MIT (permissive) · c347a1bee1e9939f · report fixture: signature img_ph:Tensor/3/float · returned Tensor · level recorded 2026-09-25
resize in 108 papers
census: 10 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
element-frame-based/sift/model.py ran fingerprinted MIT (permissive) · 4ceb2d6022efa952 · report fixture: signature patch:ndarray/3/int · returned ndarray · level recorded 2026-09-25
squeezenet1_0 in 5 papers element-frame-based/percival/ModuleSqueezeNet1.py ran MIT (permissive) · fdf8f85f406426a8 · report fixture: returned SqueezeNet · level recorded 2026-09-25
squeezenet1_1 in 6 papers element-frame-based/percival/ModuleSqueezeNet1.py ran MIT (permissive) · 43cd5c22cd650a33 · report fixture: signature pretrained:bool/0/bool, progress:bool/0/bool · returned SqueezeNet · level recorded 2026-09-25
to_gray element-frame-based/utils.py ran MIT (permissive) · 45c374c2c75105a5 · report fixture: signature logo:ndarray/3/int · returned ndarray · level recorded 2026-09-25
blend_transparent element-frame-based/utils.py unverified MIT (permissive) · f11417cdc9ea3460 · report
load_example element-frame-based/OCR/evade_or_fp_attack.py unverified MIT (permissive) · 35a4a4659ccecb7a · report
load_weights in 35 papers page-based/yolo_v3.py unverified MIT (permissive) · 968725378659c630 · report
phash_dct_tf element-frame-based/phash/model.py unverified MIT (permissive) · 4622646a7161f4cc · report

Tasks

BIG-bench Machine LearningBlocking

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