Circuit breaking post

posts/biblio.bib

@@ -253,4 +253,31 @@ @article{cammarata2020thread
   year = {2020},
   note = {https://distill.pub/2020/circuits},
   doi = {10.23915/distill.00024}
+}
+
+@article{sadasivan2024fast,
+  title={Fast Adversarial Attacks on Language Models In One GPU Minute},
+  author={Sadasivan, Vinu Sankar and Saha, Shoumik and Sriramanan, Gaurang and Kattakinda, Priyatham and Chegini, Atoosa and Feizi, Soheil},
+  journal={arXiv preprint arXiv:2402.15570},
+  year={2024}
+}
+
+@misc{zou2024improvingalignmentrobustnesscircuit,
+      title={Improving Alignment and Robustness with Circuit Breakers}, 
+      author={Andy Zou and Long Phan and Justin Wang and Derek Duenas and Maxwell Lin and Maksym Andriushchenko and Rowan Wang and Zico Kolter and Matt Fredrikson and Dan Hendrycks},
+      year={2024},
+      eprint={2406.04313},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2406.04313}, 
+}
+
+@misc{cui2024orbenchoverrefusalbenchmarklarge,
+      title={OR-Bench: An Over-Refusal Benchmark for Large Language Models}, 
+      author={Justin Cui and Wei-Lin Chiang and Ion Stoica and Cho-Jui Hsieh},
+      year={2024},
+      eprint={2405.20947},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2405.20947}, 
 }