Related papers: Scaling Trends for Data Poisoning in LLMs
In the domain of large language models (LLMs), in-context learning (ICL) has been recognized for its innovative ability to adapt to new tasks, relying on examples rather than retraining or fine-tuning. This paper delves into the critical…
As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy…
Modern large language models (LLMs) exhibit critical vulnerabilities to poison pill attacks: localized data poisoning that alters specific factual knowledge while preserving overall model utility. We systematically demonstrate these attacks…
As the number of large language models (LLMs) released to the public grows, there is a pressing need to understand the safety implications associated with these models learning from third-party custom finetuning data. We explore the…
Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…
Large Language Models (LLMs) have a privacy concern because they memorize training data (including personally identifiable information (PII) like emails and phone numbers) and leak it during inference. A company can train an LLM on its…
Large language models (LLMs) have become ubiquitous, thus it is important to understand their risks and limitations. Smaller LLMs can be deployed where compute resources are constrained, such as edge devices, but with different propensity…
This paper explores the pressing issue of risk assessment in Large Language Models (LLMs) as they become increasingly prevalent in various applications. Focusing on how reward models, which are designed to fine-tune pretrained LLMs to align…
Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on manually well-crafted prompts. LLM-based prompt optimizers…
When practitioners fine-tune LLMs on unvetted datasets, an adversary can exploit the data supply chain through task-level poisoning: inserting a small number of crafted instruction-response pairs that cause the model to embed…
While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy…
Public leaderboards increasingly suggest that large language models (LLMs) surpass human experts on benchmarks spanning academic knowledge, law, and programming. Yet most benchmarks are fully public, their questions widely mirrored across…
Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…
As large language models (LLMs) are increasingly fine-tuned for hardware tasks like RTL code generation, the scarcity of high-quality datasets often leads to the use of rapidly assembled or generated training data. These datasets frequently…
The rapid advancement of multimodal large language models (MLLMs) has significantly enhanced performance across benchmarks. However, data contamination-unintentional memorization of benchmark data during model training-poses critical…
Large language models (LLMs) have shown great potential as general-purpose AI assistants across various domains. To fully leverage this potential in specific applications, many companies provide fine-tuning API services, enabling users to…
Data poisoning and backdoor attacks manipulate training data in order to cause models to fail during inference. A recent survey of industry practitioners found that data poisoning is the number one concern among threats ranging from model…
Federated large language models (FedLLMs) enable powerful generative capabilities within wireless networks while preserving data privacy. Nonetheless, FedLLMs remain vulnerable to model poisoning attacks. This article first reviews recent…
The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…
Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…