Vulnerability of Text-Matching in ML/AI Conference Reviewer Assignments to Collusions
- URL: http://arxiv.org/abs/2412.06606v1
- Date: Mon, 09 Dec 2024 15:55:20 GMT
- Title: Vulnerability of Text-Matching in ML/AI Conference Reviewer Assignments to Collusions
- Authors: Jhih-Yi, Hsieh, Aditi Raghunathan, Nihar B. Shah,
- Abstract summary: Collusion rings pose a challenge to top-tier machine learning (ML) and artificial intelligence (AI) conferences.
We show that even in the absence of bidding, colluding reviewers and authors can exploit the machine learning based text-matching component of reviewer assignment.
- Score: 29.549766565378775
- License:
- Abstract: In the peer review process of top-tier machine learning (ML) and artificial intelligence (AI) conferences, reviewers are assigned to papers through automated methods. These assignment algorithms consider two main factors: (1) reviewers' expressed interests indicated by their bids for papers, and (2) reviewers' domain expertise inferred from the similarity between the text of their previously published papers and the submitted manuscripts. A significant challenge these conferences face is the existence of collusion rings, where groups of researchers manipulate the assignment process to review each other's papers, providing positive evaluations regardless of their actual quality. Most efforts to combat collusion rings have focused on preventing bid manipulation, under the assumption that the text similarity component is secure. In this paper, we demonstrate that even in the absence of bidding, colluding reviewers and authors can exploit the machine learning based text-matching component of reviewer assignment used at top ML/AI venues to get assigned their target paper. We also highlight specific vulnerabilities within this system and offer suggestions to enhance its robustness.
Related papers
- Illusions of Relevance: Using Content Injection Attacks to Deceive Retrievers, Rerankers, and LLM Judges [52.96987928118327]
We find that embedding models for retrieval, rerankers, and large language model (LLM) relevance judges are vulnerable to content injection attacks.
We identify two primary threats: (1) inserting unrelated or harmful content within passages that still appear deceptively "relevant", and (2) inserting entire queries or key query terms into passages to boost their perceived relevance.
Our study systematically examines the factors that influence an attack's success, such as the placement of injected content and the balance between relevant and non-relevant material.
arXiv Detail & Related papers (2025-01-30T18:02:15Z) - Analysis of the ICML 2023 Ranking Data: Can Authors' Opinions of Their Own Papers Assist Peer Review in Machine Learning? [52.00419656272129]
We conducted an experiment during the 2023 International Conference on Machine Learning (ICML)
We received 1,342 rankings, each from a distinct author, pertaining to 2,592 submissions.
We focus on the Isotonic Mechanism, which calibrates raw review scores using author-provided rankings.
arXiv Detail & Related papers (2024-08-24T01:51:23Z) - RelevAI-Reviewer: A Benchmark on AI Reviewers for Survey Paper Relevance [0.8089605035945486]
We propose RelevAI-Reviewer, an automatic system that conceptualizes the task of survey paper review as a classification problem.
We introduce a novel dataset comprised of 25,164 instances. Each instance contains one prompt and four candidate papers, each varying in relevance to the prompt.
We develop a machine learning (ML) model capable of determining the relevance of each paper and identifying the most pertinent one.
arXiv Detail & Related papers (2024-06-13T06:42:32Z) - On the Detection of Reviewer-Author Collusion Rings From Paper Bidding [71.43634536456844]
Collusion rings pose a major threat to the peer-review systems of computer science conferences.
One approach to solve this problem would be to detect the colluding reviewers from their manipulated bids.
No research has yet established that detecting collusion rings is even possible.
arXiv Detail & Related papers (2024-02-12T18:12:09Z) - No more Reviewer #2: Subverting Automatic Paper-Reviewer Assignment
using Adversarial Learning [25.70062566419791]
We show that this automation can be manipulated using adversarial learning.
We propose an attack that adapts a given paper so that it misleads the assignment and selects its own reviewers.
arXiv Detail & Related papers (2023-03-25T11:34:27Z) - Investigating Fairness Disparities in Peer Review: A Language Model
Enhanced Approach [77.61131357420201]
We conduct a thorough and rigorous study on fairness disparities in peer review with the help of large language models (LMs)
We collect, assemble, and maintain a comprehensive relational database for the International Conference on Learning Representations (ICLR) conference from 2017 to date.
We postulate and study fairness disparities on multiple protective attributes of interest, including author gender, geography, author, and institutional prestige.
arXiv Detail & Related papers (2022-11-07T16:19:42Z) - A Dataset on Malicious Paper Bidding in Peer Review [84.68308372858755]
Malicious reviewers strategically bid in order to unethically manipulate the paper assignment.
A critical impediment towards creating and evaluating methods to mitigate this issue is the lack of publicly-available data on malicious paper bidding.
We release a novel dataset, collected from a mock conference activity where participants were instructed to bid either honestly or maliciously.
arXiv Detail & Related papers (2022-06-24T20:23:33Z) - Ranking Scientific Papers Using Preference Learning [48.78161994501516]
We cast it as a paper ranking problem based on peer review texts and reviewer scores.
We introduce a novel, multi-faceted generic evaluation framework for making final decisions based on peer reviews.
arXiv Detail & Related papers (2021-09-02T19:41:47Z) - Making Paper Reviewing Robust to Bid Manipulation Attacks [44.34601846490532]
Anecdotal evidence suggests that some reviewers bid on papers by "friends" or colluding authors.
We develop a novel approach for paper bidding and assignment that is much more robust against such attacks.
In addition to being more robust, the quality of our paper review assignments is comparable to that of current, non-robust assignment approaches.
arXiv Detail & Related papers (2021-02-09T21:24:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.