We lifted 3 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| yannikbenz/zeroe | canonical | 2 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| load_pd_data | Ran | yannikbenz/zeroe/gen_datasets.py code served (permissive licence) · get_code("a26fb87dfd499ccd") |
| swap | Ran | yannikbenz/zeroe/code/attacks/simple_attacks.py code served (permissive licence) · get_code("93d1e407ec8d85e5") |
| intruders | Not yet run | yannikbenz/zeroe/code/attacks/simple_attacks.py code served (permissive licence) · get_code("b097690f3b4bbbd2") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Adversarial attacks are label-preserving modifications to inputs of machine learning classifiers designed to fool machines but not humans. Natural Language Processing (NLP) has mostly focused on high-level attack scenarios such as paraphrasing input texts. We argue that these are less realistic in typical application scenarios such as in social media, and instead focus on low-level attacks on the character-level. Guided by human cognitive abilities and human robustness, we propose the first large-scale catalogue and benchmark of low-level adversarial attacks, which we dub Zéroe, encompassing nine different attack modes including visual and phonetic adversaries. We show that RoBERTa, NLP's current workhorse, fails on our attacks. Our dataset provides a benchmark for testing robustness of future more human-like NLP models.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2010.05648")
get_code_for_paper("2010.05648")
have("2010.05648")
Connect an agent — have() is free.