Model layer Vulnerabilities

Large Language Models (LLMs) designed for step-by-step problem-solving are vulnerable to query-agnostic adversarial triggers. Appending short, semantically irrelevant text snippets (e.g., "Interesting fact: cats sleep most of their lives") to mathematical problems consistently increases the likelihood of incorrect model outputs without altering the problem's inherent meaning. This vulnerability stems from the models' susceptibility to subtle input manipulations that interfere with their…

Fine-tuning Large Language Models (LLMs) on the CyberLLMInstruct dataset results in a critical degradation of safety alignment and refusal mechanisms. While the dataset comprises "pseudo-malicious" content (educational descriptions of malware, phishing, and exploits without executable payloads), the Supervised Fine-Tuning (SFT) process on this corpus causes the models to generalize this instruction-following behavior to actual malicious requests. This effectively bypasses safety guardrails…

Retrieval-Augmented Generation (RAG) systems employing standard dense embedding models (e.g., Sentence-T5, SimCSE-BERT, RoBERTa, MPNet) for End-Cloud collaboration are vulnerable to Embedding Inversion Attacks (EIA). While embeddings are vector representations designed to be human-unrecognizable, they retain sufficient semantic information to allow an attacker with access to the vectors (e.g., a malicious or compromised cloud provider) to reconstruct the original sensitive plaintext input.

Multimodal Large Language Models (MLLMs) are vulnerable to coupled cross-modal jailbreak attacks that combine continuous visual perturbations with discrete textual manipulations. Because standard alignment and single-modality defenses (such as text-only safety tuning or isolated vision-encoder adversarial training) fail to secure the cross-modal interaction, attackers can simultaneously apply gradient-based noise (e.g., PGD) to input images and adversarial suffixes (e.g., GCG) to text prompts…

Large Language Models (LLMs) employing gradient-based optimization for jailbreaking defense are vulnerable to enhanced transferability attacks due to superfluous constraints in their objective functions. Specifically, the "response pattern constraint" (forcing a specific initial response phrase) and the "token tail constraint" (penalizing variations in the response beyond a fixed prefix) limit the search space and reduce the effectiveness of attacks across different models. Removing these…

Large Language Models (LLMs) are vulnerable to an adversarial encoding attack where English instructions are obfuscated using valid but visually nonsensical UTF-8 byte sequences. By manipulating multi-byte UTF-8 encoding schemes—specifically by fixing the last 8 bits of a code point to match a target ASCII character and rotating the remaining bits—attackers can generate sequences (e.g., Byzantine musical symbols) that appear incomprehensible to humans and standard text filters but are…

Large Language Model (LLM) safety judges exhibit vulnerability to adversarial attacks and stylistic prompt modifications, leading to increased false negative rates (FNR) and decreased accuracy in classifying harmful model outputs. Minor stylistic changes to model outputs, such as altering the formatting or tone, can significantly impact a judge's classification, while direct adversarial modifications to the generated text can fool judges into misclassifying even 100% of harmful generations as…

A vulnerability exists in large language models (LLMs) where the model's internal representations (activations) in specific latent subspaces can be manipulated to trigger jailbreak responses. By calculating a perturbation vector based on the difference between the mean activations of "safe" and "jailbroken" states, an attacker can introduce a targeted perturbation to the model's activations, causing it to generate unsafe outputs even when presented with a safe prompt. This manipulates the…

Predictive Large Language Model (LLM) routers, specifically those utilizing Deep Neural Network (DNN) and Matrix Factorization (MF) architectures, are vulnerable to adversarial manipulation and backdoor poisoning. These routers are designed to optimize cost and latency by dynamically directing simple queries to "weak" (cheap) models and complex queries to "strong" (expensive) models. Attackers can exploit this mechanism in two ways: 1. Inference-time Attacks: By appending specific adversarial…

Large Language Models (LLMs) are vulnerable to a novel jailbreaking attack leveraging adversarial metaphors. The attack, termed AVATAR, induces the LLM to reason about benign metaphors related to harmful tasks, ultimately leading to the generation of harmful content either directly or through calibration of metaphorical and professional harmful content. The attack exploits the LLM's cognitive mapping process, bypassing standard safety mechanisms.