Pith. sign in

Pith Integrity · Reference Change Desk · events-only

Reference changes

See every place this corpus cites a work that was later retracted, corrected, withdrawn, or placed under expression of concern: exact quote, event source, and what happened next. No model judges the citation.

A notice on this page means a citing paper's bibliography includes a work with a published scholarly-record event. It is not a judgment on the citing paper.

Scoped to citing paper 2502.05224 · clear

01Events with corpus notices

02One-hop citation notices (secondary index)

Correction Crossref Open
A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

cites Red alarm for pre- trained models: Universal vulnerability to neuron-level backdoor attacks, · ref [53] · event 2024-07-05 · 2502.05224 · event page · DOI 10.1007/s11633-022-1377-5

Raw extraction · bibliography line

Z. Zhang, G. Xiao, Y . Li, T. Lv, F. Qi, Z. Liu, Y . Wang, X. Jiang, and M. Sun, “Red alarm for pre- trained models: Universal vulnerability to neuron-level backdoor attacks,” Machine Intelligence Research , vol. 20, no. 2, p. 180–193, Mar. 2023. [Online]. Available: http://dx.doi.org/10.1007/s11633-022-1377-5

Parser render (TeX stripped for reading; raw above is the evidence)

Z. Zhang, G. Xiao, Y . Li, T. Lv, F. Qi, Z. Liu, Y . Wang, X. Jiang, and M. Sun, “Red alarm for pre- trained models: Universal vulnerability to neuron-level backdoor attacks,” Machine Intelligence Research, vol. 20, no. 2, p. 180–193, Mar. 2023. [Online]. Available: http://dx.doi.org/10.1007/s11633-022-1377-5