paper-with-me

홈 › Papers

Influence Based Defense Against Data Poisoning Attacks in Online Learning

2021-04-24 · Sanjay Seetharaman, Shubham Malaviya, Rosni KV, Manish Shukla, Sachin Lodha

Data poisoning is a type of adversarial attack on training data where an attacker manipulates a fraction of data to degrade the performance of machine learning model. Therefore, applications that rely on external data-sources for training data are at a significantly higher risk. There are several known defensive mechanisms that can help in mitigating the threat from such attacks. For example, data sanitization is a popular defensive mechanism wherein the learner rejects those data points that are sufficiently far from the set of training instances. Prior work on data poisoning defense primarily focused on offline setting, wherein all the data is assumed to be available for analysis. Defensive measures for online learning, where data points arrive sequentially, have not garnered similar interest. In this work, we propose a defense mechanism to minimize the degradation caused by the poisoned training data on a learner's model in an online setup. Our proposed method utilizes an influence function which is a classic technique in robust statistics. Further, we supplement it with the existing data sanitization methods for filtering out some of the poisoned data points. We study the effectiveness of our defense mechanism on multiple datasets and across multiple attack strategies against an online learner.

📄 PDF Abstract BibTeX arXiv:2104.13230

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackData Poisoning

Similar Papers 제목 키워드 기반

HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks

2023-09-15 · Minh-Hao Van, Alycia N. Carey, Xintao Wu

While numerous defense methods have been proposed to prohibit potential poisoning attacks from untrusted data sources, most research works only defend against specific attacks, which leaves many avenues for an adversary …

Data Poisoning

Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning

2018-04-01 · Matthew Jagielski, Alina Oprea, Battista Biggio, Chang Liu 외

As machine learning becomes widely used for automated decisions, attackers have strong incentives to manipulate the results and models generated by machine learning algorithms. In this paper, we perform the first systema…

BIG-bench Machine Learningregression

Deep Partition Aggregation: Provable Defense against General Poisoning Attacks

2020-06-26 · Alexander Levine, Soheil Feizi

Adversarial poisoning attacks distort training data in order to corrupt the test-time behavior of a classifier. A provable defense provides a certificate for each test sample, which is a lower bound on the magnitude of a…

Stronger Data Poisoning Attacks Break Data Sanitization Defenses

2018-11-02 · Pang Wei Koh, Jacob Steinhardt, Percy Liang

Machine learning models trained on data from the outside world can be corrupted by data poisoning attacks that inject malicious points into the models' training sets. A common defense against these attacks is data saniti…

Data PoisoningSentiment AnalysisSentiment ClassificationSpam detection

Turning Generative Models Degenerate: The Power of Data Poisoning Attacks

2024-07-17 · Shuli Jiang, Swanand Ravindra Kadhe, Yi Zhou, Farhan Ahmed 외

The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through poisoning attacks to generate undesirable …

Data Poisoningparameter-efficient fine-tuningText GenerationText Summarization