Fabio Roli, Battista Biggio, Blaine Nelson, Pavel Laskov, Nedim Šrndić, Igino Corona, Davide Maiorca, Giorgio Giacinto
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system at test time by carefully manipulating attack samples. In this work, we present a simple but effective gradientbased approach that can be exploited to systematically assess the security of several, widely-used classification algorithms against evasion attacks. Following a recently proposed framework for security evaluation, we simulate attack scenarios that exhibit different risk levels for the classifier by increasing the attacker's knowledge of the system and her ability to manipulate attack samples. This gives the classifier designer a better picture of the classifier performance under evasion attacks, and allows him to perform a more informed model selection (or parameter setting). We evaluate our approach on the relevant security task of malware detection in PDF files, and show that such systems can be easily evaded. We also sketch some countermeasures suggested by our analysis.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1708.06131")
get_code_for_paper("1708.06131")
have("1708.06131")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1708.06131.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1708.06131)
Connect an agent — have() is free.