Pith. sign in

Researcher Evidence Record

Ambra Demontis

This bounded record lists 34 Pith paper rows and 0 imported work rows attributed to this corpus identity. The enumerated, non-disputed paper rows include cs.LG, cs.CR, cs.CV work dated 2017 to 2026. The record describes sources and coverage; it makes no judgment about the person.

Compiled coverage vector

Measured lane counts only. Not a trust score or person verdict.

Identity 2 canonical identity row plus typed public identifiers Pith papers 34 attributed paper rows in the Pith corpus, itemized below Imported works 0 imported works beyond the paper ledger Current reviews 2 of 34 papers carrying a current Pith review; presence, not outcome Sourced citations 3 of 34 works with a source-named citation count Coauthors 50 distinct coauthors across shared paper rows
Enumerated paper scope: 5 fields (cs.LG, cs.CR, cs.CV, +2 more) · 2017-2026 sources: authors, author_identifiers · paper_authors · author_works · current_verdicts · cited_works

A sourced case file for attributed work. It is neither a profile score nor a verdict about this researcher.

Attributed works

A bounded ledger from the Pith paper and imported-work queries. Counts and source confidence stay with each work.

  1. 2026 Pith paper

    Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation

    cs.LG provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  2. 2025 Pith paper

    Prototype-Guided Robust Learning against Backdoor Attacks

    cs.CR provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Ambra Demontis
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  3. 2025 Pith paper

    Evaluating the Evaluators: Trust in Adversarial Robustness Tests

    cs.CR provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  4. 2024 Pith paper

    Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  5. 2024 Pith paper

    A Hybrid Training-time and Run-time Defense Against Adversarial Attacks in Modulation Classification

    cs.AI provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  6. 2024 Pith paper

    Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    10
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  7. 2024 Pith paper

    AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  8. 2023 Pith paper

    Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  9. 2023 Pith paper

    Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  10. 2023 Pith paper

    Hardening RGB-D Object Recognition Systems against Adversarial Patch Attacks

    cs.CV provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    7
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  11. 2023 Pith paper

    Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  12. 2022 Pith paper

    Stateful Detection of Adversarial Reprogramming

    cs.GT provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  13. 2022 Pith paper

    Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  14. 2022 Pith paper

    Machine Learning Security against Data Poisoning: Are We There Yet?

    cs.CR provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  15. 2022 Pith paper

    Energy-Latency Attacks via Sponge Poisoning

    cs.CR provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  16. 2022 Pith paper

    ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches

    cs.CR provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  17. 2021 Pith paper

    Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  18. 2021 Pith paper

    The Threat of Offensive AI to Organizations

    cs.AI provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  19. 2021 Pith paper

    Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  20. 2021 Pith paper

    Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  21. 2021 Pith paper

    BAARD: Blocking Adversarial Examples by Testing for Applicability, Reliability and Decidability

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  22. 2021 Pith paper

    The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  23. 2020 Pith paper

    Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  24. 2020 Pith paper

    Do Gradient-based Explanations Tell Anything About Adversarial Robustness to Android Malware?

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  25. 2019 Pith paper

    secml: A Python Library for Secure and Explainable Machine Learning

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  26. 2019 Pith paper

    Deep Neural Rejection against Adversarial Examples

    cs.CV provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  27. 2018 Pith paper

    Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 2 pith inbound references from cited_work_pith_inbound_counts
  28. 2018 Pith paper

    Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables

    cs.CR provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  29. 2017 Pith paper

    Super-sparse Learning in Similarity Spaces

    cs.CV provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  30. 2017 Pith paper

    Adversarial Detection of Flash Malware: Limitations and Open Issues

    cs.CR provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  31. 2017 Pith paper

    On Security and Sparsity of Linear Classifiers for Adversarial Settings

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  32. 2017 Pith paper

    Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  33. 2017 Pith paper

    Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoid

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  34. 2017 Pith paper

    Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection

    cs.CR provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Ambra Demontis
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.

Evidence apparatus

The machinery behind this record. Every lane states whether Pith measured it, did not query it, could not reach it, or withheld it.

LaneStateObservedBoundary and source
identity Measured 2 Canonical identity row plus public typed identifiers.
source=authors, author_identifiers
papers Measured 34 of 34 bounded rows Rows attributed to this author UUID in the Pith corpus.
source=paper_authors
works Measured zero 0 of 0 bounded rows Imported works not duplicated by the paper ledger.
source=author_works
reviews Measured 2 of 34 bounded rows Coverage count only. No review outcome is projected onto the person.
source=current_verdicts
citations Measured 3 of 34 bounded rows Counts remain itemized by work and source.
source=cited_works
coauthors Measured 50 of 34 bounded rows Shared-work edges from admitted paper rows.
source=paper_authors
account Unavailable No public count of 1 bounded rows Account metadata is separate from corpus evidence.
source=users.author_id
Public identity sources
  • name variant
    Ambra Demontis     backfill
    confidence 0.6

identity history

Enumerated research scope

Fields and dates come only from enumerated, non-disputed Pith paper rows. They do not claim career completeness.

  • cs.LG20 rows
  • cs.CR8 rows
  • cs.CV3 rows
  • cs.AI2 rows
  • cs.GT1 rows
  • 20176 rows
  • 20182 rows
  • 20192 rows
  • 20202 rows
  • 20216 rows
  • 20225 rows
  • 20234 rows
  • 20244 rows
  • 20252 rows
  • 20261 rows
Shared-work index
Record scope

The work queries are bounded. Missing rows may mean measured zero, an unavailable source, a query that did not run, or private data that Pith withheld. The lane table keeps those cases separate.

Paper findings remain attached to papers. They do not become findings about this researcher.