REVIEW 8 cited by
Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent advances in the development of large language models have resulted in public access to state-of-the-art pre-trained language models (PLMs), including Generative Pre-trained Transformer 3 (GPT-3) and Bidirectional Encoder Representations from Transformers (BERT). However, evaluations of PLMs, in practice, have shown their susceptibility to adversarial attacks during the training and fine-tuning stages of development. Such attacks can result in erroneous outputs, model-generated hate speech, and the exposure of users' sensitive information. While existing research has focused on adversarial attacks during either the training or the fine-tuning of PLMs, there is a deficit of information on attacks made between these two development phases. In this work, we highlight a major security vulnerability in the public release of GPT-3 and further investigate this vulnerability in other state-of-the-art PLMs. We restrict our work to pre-trained models that have not undergone fine-tuning. Further, we underscore token distance-minimized perturbations as an effective adversarial approach, bypassing both supervised and unsupervised quality measures. Following this approach, we observe a significant decrease in text classification quality when evaluating for semantic similarity.
Forward citations
Cited by 8 Pith papers
-
When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents
A trained attack model generates single emails that silently inject false memories into persistent AI agents, achieving 87.5% end-to-end success on GPT-5.4 and transferring across architectures and memory backends.
-
Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels
Indirect prompt injection through ads, webviews, and notifications reliably diverts mobile LLM agents into leaking data and installing malware across eight evaluated agents.
-
When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents
The paper claims prompt compression is a new attack surface, but the abstract's COMA attack never appears in the body and the body's SoftCom requires white-box access.
-
Understanding the Ability of LLMs to Handle Character-Level Perturbation
LLMs remain surprisingly accurate on math and coding when invisible Unicode noise is inserted after every character, with robustness driven by implicit internal denoising and, for some models, explicit rewriting in ch...
-
When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue Generation
A systematic evaluation shows that masking the interlocutor's persona lowers target speaker identification accuracy, and that zero-shot models often copy biography details, making identification easier but dialogues m...
-
We Can't Understand AI Using our Existing Vocabulary
AI interpretability is reframed as building a shared human-machine language in which each new word is a learned token embedding trained by preference optimization.
-
PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training
A PRM-free alignment pipeline combining genetic algorithm red teaming and multi-objective adversarial training is claimed to beat PRM-based methods at 61% lower cost, but the experiments are unverifiable.
-
Prompt Injection 2.0: Hybrid AI Threats
A structured taxonomy of hybrid prompt injection attacks shows how XSS, CSRF, and SQL injection vectors converge with LLM manipulation to bypass traditional controls.
Discussion (0). Continue with ORCID to comment.