Papers with defensive strategy
MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown exceptional results when working individually, and have reduced parameter size and inference times. |
| Approach: | They evaluate the behavior of a network of models collaborating through debate under the influence of an adversary and examine inference-time methods to generate more compelling arguments. |
| Outcome: | The proposed model-based model-driven analysis shows that the model-led model-mediated debates generate more compelling arguments and provide a defensive strategy. |
Learn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks (2022.coling-1)
Copied to clipboard
| Challenge: | Prior black-box adversarial attacks assume that attackers can observe output labels from target models based on selected inputs. |
| Approach: | They propose a black-box adversarial attack where an attacker can transfer adversarials to a target domain and cause poor performance in target model. |
| Outcome: | The proposed attack is effective against similar-domain adversarial examples compared to standard black-box defense methods such as adversarials training and defense distillation. |
‘Quis custodiet ipsos custodes?’ Who will watch the watchmen? On Detecting AI-generated peer-reviews (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have focused on generic AI-generated text detection or estimating fraction of peer-reviews that can be AI-generated. |
| Approach: | They propose a model that detects whether a peer-review is written by ChatGPT and a reviewer-generated model that generates similar outputs upon re-prompting. |
| Outcome: | The proposed model is more robust, but paraphrasing is more effective. |