Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Large Language Models and Vision Language Model (LLMs) have impressive performance across a wide range of tasks, yet remain vulnerable to external and internal perturbations. |
| Approach: | They propose a stability measure called FI, First order local Influence, which quantifies the sensitivity of individual parameters and input dimensions. |
| Outcome: | The proposed stability measure measures the sensitivity of parameters and input dimensions across LLMs and VLMs. |
Similar Papers
Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective (2025.coling-main)
Copied to clipboard
Tianlong Li, Zhenghua Wang, Wenhao Liu, Muling Wu, Shihan Dou, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) however, limited research into the underlying mechanisms that make LLMs vulnerable to such attacks has been conducted. |
| Approach: | They propose that LLMs' self-safeguarding capability is linked to specific activity patterns within their representation space. |
| Outcome: | The proposed models can be detected with a few pairs of contrastive queries, and the robustness can be manipulated by weakening or strengthening these patterns. |
Vulnerabilities of Large Language Models to Adversarial Attacks (2024.acl-tutorials)
Copied to clipboard
| Challenge: | This tutorial focuses on the vulnerabilities of Large Language Models to adversarial attacks . the tutorial lays the foundation by explaining safety-aligned models and concepts in cybersecurity . |
| Approach: | This tutorial lays the foundation by explaining safety-aligned LLMs and concepts in cybersecurity. |
| Outcome: | The tutorial lays the foundation by explaining safety-aligned models and concepts in cybersecurity. |
Tokenization Falling Short: On Subword Robustness in Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Language models typically tokenize raw text into sequences of subword identifiers from a predefined vocabulary. |
| Approach: | They propose to tokenize raw text into sequences of subword identifiers from a predefined vocabulary . they also investigate the challenges and their impact on large language models . |
| Outcome: | The proposed model can mitigate tokenization issues, but still suffer from typos and other variations. |
Evaluating Concurrent Robustness of Language Models Across Diverse Challenge Sets (2024.emnlp-main)
Copied to clipboard
| Challenge: | Language models display sensitivity to input perturbations, causing concerns about trust among users. |
| Approach: | They propose a methodology to examine how input perturbations affect language models across various scales, including pre-trained models and large language models. |
| Outcome: | The proposed methods enhance the model’s robustness to input perturbations and if exposure to one perturbation enhances or diminishes its performance with respect to other perturbations. |
Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Understanding how jailbreaking works remains limited, hindering the development of effective defense strategies. |
| Approach: | They propose a new mechanism that adaptively constrains activations within the safety boundary and propose 'Activation Boundary Defense' to enhance its effectiveness. |
| Outcome: | The proposed defense achieves an average Defense Success Rate (DSR) of over 98% against various jailbreak attacks, with less than 2% impact on the model’s general capabilities. |
Resilience of Large Language Models for Noisy Instructions (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) are powerful tools for interpreting human commands and generating text. |
| Approach: | They examine the resilience of large language models against five common types of disruptions including ASR, OCR, grammatical errors, typographical errors and distractive content. |
| Outcome: | The models show resistance to noise, but their performance suffers . authors evaluated the models against five common types of disruptions based on their results . |
The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts (2024.findings-acl)
Copied to clipboard
Lingfeng Shen, Weiting Tan, Sihao Chen, Yunmo Chen, Jingyu Zhang, Haoran Xu, Boyuan Zheng, Philipp Koehn, Daniel Khashabi
| Challenge: | Recent studies show that malicious prompt instructions could solicit objectionable content from LLMs. |
| Approach: | They compare how state-of-the-art LLMs respond to malicious prompts in different languages . they find that LLM's generate unsafe responses more often when a prompt is written in a lower-resource language . |
| Outcome: | The proposed model can generate unsafe responses more often when a malicious prompt is written in a lower-resource language, and less irrelevant responses when written in lower-source languages. |
Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing safety-related methodologies for large language models are lacking . despite advances in safety alignment techniques, safeguarding LLMs during adaptation to various tasks remains a challenge. |
| Approach: | They propose a framework to quantify how different parameters affect LLM safety . they propose two targeted intervention paradigms for safety enhancement and preservation . |
| Outcome: | The proposed framework reveals safety-critical patterns across different LLM architectures. |
Safety of Large Language Models Beyond English: A Systematic Literature Review of Risks, Biases, and Safeguards (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have a growing number of applications that generate harmful, biased, or unsafe content. |
| Approach: | They synthesize findings from recent studies that evaluate their robustness across languages . they highlight gaps in multilingual safety research and recommend future work . |
| Outcome: | The systematic review examines the multilingual safety of large language models in English . it identifies challenges such as dataset availability and evaluation biases . |
Why Safeguarded Ships Run Aground? Aligned Large Language Models’ Safety Mechanisms Tend to Be Anchored in The Template Region (2025.acl-long)
Copied to clipboard
| Challenge: | Infilling a fixed template between the input instruction and initial model output is a common practice for existing LLMs, but it is vulnerable to inference-time jailbreak attacks. |
| Approach: | They propose to fill a fixed template between the input instruction and initial model output and to detach safety mechanisms from the template region to mitigate the risk of inference-time jailbreak attacks. |
| Outcome: | The proposed method is widespread across aligned LLMs and shows that it mitigates inference-time jailbreak vulnerabilities. |