Aniruddha Saha

Aniruddha Saha has 3 papers in our library, in 2023–2024, most of them on Language models & pretraining; often with Jonas Geiping, Micah Goldblum, Tom Goldstein.

3 papers in our library · 2023–2024

No OpenAlex profile matched yet.

The profile is the library's match of the name; two people with one name are not always told apart.

Fields, topics and concepts

Of its works in our library, with the number of works on each.

The most cited first (OpenAlex and our library).

Baseline Defenses for Adversarial Attacks Against Aligned Language Models (2023 · 236 citations)
Optimization-based jailbreaks, especially the universal, transferable suffix attack (GCG) of Zou et al. (2023), can automatically generate prompts that bypass the safety alignment of chat LLMs. These prompts can be crafted on open models and then used against API-only systems. The authors ask whether standard defense…
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text (2024 · 120 citations)
The paper addresses how to tell machine-written text from human writing when no examples from the generating model are available.
On the Reliability of Watermarks for Large Language Models (2023 · 103 citations)
Spotting machine-generated text helps limit spam, bot activity and contamination of future training data. Earlier watermark evaluations, however, mostly assumed the detector receives unmodified model output. This paper tests whether the green-list watermark of Kirchenbauer et al. (2023) survives realistic handling…

8 co-authors with a page, the most papers together first.

Papers of our library cite their works 388 times (of the 149,439 papers whose bibliographies we read); 100 citing papers with a page here →.

Updated 2 November 2026