Benchmarking the Effect of Poisoning Defenses on the Security and Bias of Deep Learning Models
- Nathalie Baracaldo Angel
- Farhan Ahmed
- et al.
- 2023
- S&P 2023
Bio
I am a research scientist/research staff member (RS/RSM) at IBM T. J. Watson Research Center. I'm working on many subareas of artificial intelligence, and specifically my research interests include knowledge graph construction, information extraction, trustworthy AI, and foundation models, and many other subjects of machine learning and natural language processing.
Publications
Benchmarking the Effect of Poisoning Defenses on the Security and Bias of the Final Model
- Nathalie Baracaldo Angel
- Kevin Eykholt
- et al.
- 2022
- NeurIPS 2022
Full-Stack Information Extraction System for Cybersecurity Intelligence
- 2022
- EMNLP 2022
Backdoor smoothing: Demystifying backdoor attacks on deep neural networks
- Kathrin Grosse
- Taesung Lee
- et al.
- 2022
- Computers and Security
Adaptive Verifiable Training Using Pairwise Class Similarity
- Shiqi Wang
- Kevin Eykholt
- et al.
- 2021
- AAAI 2021
Supervising unsupervised open information extraction models
- Arpita Roy
- Youngja Park
- et al.
- 2019
- EMNLP-IJCNLP 2019
AdvIT: Adversarial frames identifier based on temporal consistency in videos
- Chaowei Xiao
- Ruizhi Deng
- et al.
- 2019
- ICCV 2019
Defending against neural network model stealing attacks using deceptive perturbations
- Taesung Lee
- Benjamin Edwards
- et al.
- 2019
- SPW 2019
Detecting backdoor attacks on deep neural networks by activation clustering
- Bryant Chen
- Wilka Carvalho
- et al.
- 2019
- SafeAI 2019
List intersection for web search: Algorithms, cost models, and optimizations
- Sunghwan Kim
- Taesung Lee
- et al.
- 2017
- VLDB 2017
Patents
Measuring Overfitting Of Machine Learning Computer Model And Susceptibility To Security Threats
- 07 Nov 2022
- US
- 11494496
Deep Neural Network Hardening Framework
- 12 Sep 2022
- US
- 11443178
Protecting Cognitive Systems From Gradient Based Attacks Through The Use Of Deceiving Gradients
- 14 Apr 2022
- JP
- 7059368
Recurrent Neural Network Based Anomaly Detection
- 11 Apr 2022
- US
- 11301563
Detecting Poisoning Attacks On Neural Networks By Activation Clustering
- 29 Nov 2021
- US
- 11188789
Deep Embedding For Natural Language Content Based On Semantic Dependencies
- 22 Nov 2021
- US
- 11182562
Two-level Sequence Learning For Analyzing, Metering, Generating, And Cracking Passwords
- 08 Nov 2021
- US
- 11171946
Malware Clustering Approaches Based On Cognitive Computing Techniques
- 25 Oct 2021
- US
- 11159547
Cross-subject Model-generated Training Data For Relation Extraction Modeling
- 27 Sep 2021
- US
- 11132507
Using Gradients To Detect Backdoors In Neural Networks
- 27 Sep 2021
- US
- 11132444
Top collaborators
YP
Youngja Park
Principal Research Staff Member
JJ
Jiyong Jang
Principal Research Scientist & Manager, Cyber Security Intelligence