250 citations · 863 across the 66 of their papers we have counts for
12 papers · 1 filter
SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement
Quoc Viet Vo, Trung Le, Damith C. Ranasinghe +1
Despite the significant efforts devoted to aligning large language models (LLMs) with human values and ensuring safe deployment, recent work has revealed that LLMs remain vulnerabl…
Reasoning Errors Have a Region and a Direction in the Residual-Stream Trajectory of LLMs
Hamed Damirchi, Ignacio Meza De la Jara, Damith Ranasinghe +2
As language models are increasingly used for tasks that require verifiable reasoning, reliably distinguishing sound reasoning from flawed reasoning has become an important practica…
Certified but Fooled! Breaking Certified Defences with Ghost Certificates
Quoc Viet Vo, Tashreque M. Haq, Paul Montague +3
Certified defenses promise provable robustness guarantees. We study the malicious exploitation of probabilistic certification frameworks to better understand the limits of guarante…
Bayesian Low-Rank LeArning (Bella): A Practical Approach to Bayesian Neural Networks
Bao Gia Doan, Afshar Shamsi, Xiao-Yu Guo +6
Computational complexity of Bayesian learning is impeding its adoption in practical, large-scale tasks. Despite demonstrations of significant merits such as improved robustness and…
BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack
Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe
We study the unique, less-well understood problem of generating sparse adversarial samples simply by observing the score-based replies to model queries. Sparse attacks aim to disco…
Query Efficient Decision Based Sparse Attacks Against Black-Box Deep Learning Models
Viet Quoc Vo, Ehsan Abbasnejad, Damith C. Ranasinghe
Despite our best efforts, deep learning models remain highly vulnerable to even tiny adversarial perturbations applied to the inputs. The ability to extract information from solely…